ID,Category,Synomyms,Related synonyms,Name,ExactSynonym and label identical,description jaccard diff,Legacy Description,description details comment,Claude opus Aristotelian definition,Curated Claude opus Aristotelian definition,Reference (DOI),Layers comment,layer parts,Parent
ID,AI oio:inSubset  SPLIT=|,A oio:hasExactSynonym SPLIT=|,A oio:hasRelatedSynonym SPLIT=|,LABEL,,,,A rdfs:comment,,A IAO:0000115,>AI oio:hasDbXref  SPLIT=|,A rdfs:comment,SC BFO:0000051 some % SPLIT=|,SC % SPLIT=|
AIO:ComputationalBias,AIO:BiasSubset,Statistical Bias,,Computational Bias,FALSE,0.29,,,A bias caused by differences between results and facts in the process of data analysis (including the source of data the estimator chose) and analysis methods.,A bias caused by differences between results and facts in the process of data analysis (including the source of data the estimator chose) and analysis methods.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:Bias
AIO:IndividualBias,AIO:BiasSubset,,,Individual Bias,FALSE,0.32,"A persistent point of view or limited list of such points of view applied by an individual, such as ""parent,"" ""academic,"" or ""professional.""",,A persistent point of view or limited list of such points of view applied by an individual.,"A bias characterized by a persistent point of view or limited list of such points of view, applied by an individual.",https://develop.consumerium.org/wiki/Individual_bias,,,AIO:Bias
AIO:SocietalBias,AIO:BiasSubset,,,Societal Bias,FALSE,0.33,"Bias characterized by being for or against groups or individuals based on social identities, demographic factors, or immutable physical characteristics, often manifesting as stereotypes.",,A bias characterized by being for or against groups or individuals based on social identities demographic factors or immutable physical characteristics often manifesting as stereotypes.,A systemic bias characterized by being for or against groups or individuals based on social identities demographic factors or immutable physical characteristics often manifesting as stereotypes.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SystemicBias
AIO:HistoricalBias,AIO:BiasSubset,,,Historical Bias,FALSE,0.69,"Long-standing biases encoded in society over time, distinct from biases in historical description or the interpretation of history, such as viewing the larger world from a Western or European perspective.","Long-standing biases encoded in society over time, distinct from biases in historical description or the interpretation of history, such as viewing the larger world from a Western or European perspective.",A bias characterized by long-standing biases encoded in society over time distinct from biases in historical description or interpretation.,A bias characterized by long-standing biases encoded in society over time distinct from biases in historical description or interpretation.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:Bias
AIO:SunkCostFallacyBias,AIO:BiasSubset,Sunk Cost Fallacy,,Sunk Cost Fallacy Bias,FALSE,0.40,"The tendency to continue an endeavor due to previously invested resources, despite costs outweighing benefits.","The tendency to continue an endeavor due to previously invested resources, despite costs outweighing benefits.",A bias characterized by the tendency to continue an endeavor due to previously invested resources despite costs outweighing benefits.,A bias characterized by the tendency to continue an endeavor due to previously invested resources despite costs outweighing benefits.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:InstitutionalBias,AIO:BiasSubset,,,Institutional Bias,FALSE,0.43,"Bias exhibited at the level of entire institutions, where practices or norms result in the favoring or disadvantaging of certain social groups, such as institutional racism or sexism.","Bias exhibited at the level of entire institutions, where practices or norms result in the favoring or disadvantaging of certain social groups, such as institutional racism or sexism.",A bias exhibited at the level of entire institutions where practices or norms result in the favoring or disadvantaging of certain social groups.,A systemic bias exhibited at the level of entire institutions where practices or norms result in the favoring or disadvantaging of certain social groups.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SystemicBias
AIO:HumanBias,AIO:BiasSubset,,,Human Bias,FALSE,0.39,"Systematic errors in human thought based on heuristic principles, leading to simplified judgmental operations.",,A systematic error in human thought based on heuristic principles leading to simplified judgmental operations.,A bias in human thought based on heuristic principles leading to simplified judgmental operations.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:Bias
AIO:SystemicBias,AIO:BiasSubset,,,Systemic Bias,FALSE,0.15,Biases resulting from procedures and practices of particular institutions that operate in ways which result in certain social groups being advantaged or favored and others being disadvantaged or devalued.,,A bias resulting from procedures and practices of institutions that operate in ways which result in certain social groups being advantaged or favored and others being disadvantaged or devalued.,A bias resulting from procedures and practices of systems that operate in ways which result in certain social groups being advantaged or favored and others being disadvantaged or devalued.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:Bias
AIO:DunningKrugerEffectBias,AIO:BiasSubset,Dunning-Kruger Effect,,Dunning-Kruger Effect Bias,FALSE,#N/A,,,A cognitive bias in which people with low ability in an area overestimate that ability. Often measured by comparing self-assessment with objective performance.,A cognitive bias in which people with low ability in an area overestimate that ability. Often measured by comparing self-assessment with objective performance.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:CognitiveBias
AIO:UseAndInterpretationBias,AIO:BiasSubset,Interpretive Bias,,Use And Interpretation Bias,FALSE,0.67,"Bias inappropriately analyzing ambiguous stimuli, scenarios, and events.","Bias inappropriately analyzing ambiguous stimuli, scenarios, and events.",A computational bias characterized by inappropriately analyzing ambiguous stimuli scenarios and events.,A computational bias characterized by inappropriately analyzing ambiguous stimuli scenarios and events.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:ComputationalBias
AIO:SelectionAndSamplingBias,AIO:BiasSubset,Selection Bias|Sampling Bias|Selection Effect,,Selection And Sampling Bias,FALSE,0.50,"Bias introduced by non-random selection of individuals, groups, or data, failing to ensure representativeness.","Bias introduced by non-random selection of individuals, groups, or data, failing to ensure representativeness.",A computational bias introduced by non-random selection of individuals groups or data failing to ensure representativeness.,A computational bias introduced by non-random selection of individuals groups or data failing to ensure representativeness.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:ComputationalBias
AIO:ProcessingBias,AIO:BiasSubset,Validation Bias,,Processing Bias,FALSE,0.59,"Judgment modulated by affect, influenced by the level of efficacy and efficiency in information processing; often referred to as aesthetic judgment in cognitive sciences.","Judgment modulated by affect, influenced by the level of efficacy and efficiency in information processing; often referred to as aesthetic judgment in cognitive sciences.",A computational bias resulting from judgment modulated by affect influenced by the level of efficacy and efficiency in information processing.,A computational bias resulting from judgment modulated by affect influenced by the level of efficacy and efficiency in information processing.,https://en.wikipedia.org/wiki/Bias_(statistics),,,AIO:ComputationalBias
AIO:FundingBias,AIO:BiasSubset,,,Funding Bias,FALSE,0.14,Bias arising when biased results are reported to support or satisfy the funding agency or financial supporter of a research study.,,A bias arising when biased results are reported to support or satisfy the funding agency or financial supporter of a research study.,A group bias arising when biased results are reported to support or satisfy the funding agency or financial supporter of a research study.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:GroupBias
AIO:DeploymentBias,AIO:BiasSubset,,,Deployment Bias,FALSE,0.36,"Arises when systems are used as decision aids for humans, since the human intermediary may act on predictions in ways that are typically not modeled in the system. However, it is still individuals using the deployed system.",,A bias arising when systems are used as decision aids for humans since the human intermediary may act on predictions in ways that are typically not modeled in the system.,A group bias arising when systems are used as decision aids for humans since the human intermediary may act on predictions in ways that are typically not modeled in the system.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:GroupBias
AIO:GroupthinkBias,AIO:BiasSubset,Groupthink,,Groupthink Bias,FALSE,0.00,A psychological phenomenon where people in a group make non-optimal decisions due to a desire to conform or fear of dissent.,,A psychological phenomenon where people in a group make non-optimal decisions due to a desire to conform or fear of dissent.,A group bias in which people in a group make non-optimal decisions due to a desire to conform or fear of dissent.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:GroupBias
AIO:GroupBias,AIO:BiasSubset,In-group Favoritism|In-group–out-group Bias|In-group bias|Intergroup bias|In-group preference,,Group Bias,FALSE,0.48,"Favoring members of one's in-group over out-group members, expressed in evaluation, resource allocation, and other ways.","Favoring members of one's in-group over out-group members, expressed in evaluation, resource allocation, and other ways.",A bias characterized by favoring members of one's in-group over out-group members expressed in evaluation resource allocation and other ways.,A systemic bias characterized by favoring members of one's in-group over out-group members expressed in evaluation resource allocation and other ways.,https://en.wikipedia.org/wiki/In-group_favoritism,,,AIO:SystemicBias
AIO:InheritedBias,AIO:BiasSubset,,,Inherited Bias,FALSE,0.30,"Bias arising when machine learning applications generate inputs for other machine learning algorithms, passing on any existing bias.",,A processing bias arising when machine learning applications generate inputs for other machine learning algorithms passing on any existing bias.,A processing bias arising when machine learning applications generate inputs for other machine learning algorithms passing on any existing bias.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:ProcessingBias
AIO:AmplificationBias,AIO:BiasSubset,,,Amplification Bias,FALSE,0.22,Bias arising when the distribution over prediction outputs is skewed compared to the prior distribution of the prediction target.,,A processing bias arising when the distribution over prediction outputs is skewed compared to the prior distribution of the prediction target.,A processing bias arising when the distribution over prediction outputs is skewed compared to the prior distribution of the prediction target.,https://royalsocietypublishing.org/doi/10.1098/rspb.2019.0165#d1e5237,,,AIO:ProcessingBias
AIO:ErrorPropagationBias,AIO:BiasSubset,Error Propagation,,Error Propagation Bias,FALSE,0.33,"The effect of variables' uncertainties (or errors, more specifically random errors) on the uncertainty of a function based on them.",,A processing bias characterized by the effect of variables' uncertainties (or errors more specifically random errors) on the uncertainty of a function based on them.,A processing bias characterized by the effect of variables' uncertainties (or errors more specifically random errors) on the uncertainty of a function based on them.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:ProcessingBias
AIO:SurvivorshipBias,AIO:BiasSubset,,,Survivorship Bias,FALSE,0.48,"The tendency to focus on items, observations, or people that ""survive"" a selection process, overlooking those that did not.","The tendency to focus on items, observations, or people that ""survive"" a selection process, overlooking those that did not.","A processing bias characterized by the tendency to focus on items observations or people that ""survive"" a selection process overlooking those that did not.","A processing bias characterized by the tendency to focus on items observations or people that ""survive"" a selection process overlooking those that did not.",https://doi.org/10.6028/NIST.SP.1270,,,AIO:ProcessingBias
AIO:ModelSelectionBias,AIO:BiasSubset,,,Model Selection Bias,FALSE,0.21,"Bias introduced when using data to select a single ""best"" model from many, or when an explanatory variable has a weak relationship with the response variable.",,"A processing bias introduced when using data to select a single ""best"" model from many or when an explanatory variable has a weak relationship with the response variable.","A processing bias introduced when using data to select a single ""best"" model from many or when an explanatory variable has a weak relationship with the response variable.",https://doi.org/10.6028/NIST.SP.1270,,,AIO:ProcessingBias
AIO:DataGenerationBias,AIO:BiasSubset,,,Data Generation Bias,FALSE,0.41,Bias from adding synthetic or redundant data samples to a dataset.,Bias from adding synthetic or redundant data samples to a dataset.,A selection and sampling bias arising from adding synthetic or redundant data samples to a dataset.,A selection and sampling bias arising from adding synthetic or redundant data samples to a dataset.,https://en.wikipedia.org/wiki/Selection_bias,,,AIO:SelectionAndSamplingBias
AIO:TemporalBias,AIO:BiasSubset,,,Temporal Bias,FALSE,0.36,Bias arising from differences in populations and behaviors over time.,,A selection and sampling bias arising from differences in populations and behaviors over time.,A selection and sampling bias arising from differences in populations and behaviors over time.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SelectionAndSamplingBias
AIO:MeasurementBias,AIO:BiasSubset,,,Measurement Bias,FALSE,0.33,"Bias arising when features and labels are proxies for desired quantities, potentially leading to differential performance.",,A selection and sampling bias arising when features and labels are proxies for desired quantities potentially leading to differential performance.,A selection and sampling bias arising when features and labels are proxies for desired quantities potentially leading to differential performance.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SelectionAndSamplingBias
AIO:EvaluationBias,AIO:BiasSubset,,,Evaluation Bias,FALSE,0.29,Bias arising when testing populations do not equally represent user populations or when inappropriate performance metrics are used.,,A selection and sampling bias arising when testing populations do not equally represent user populations or when inappropriate performance metrics are used.,A selection and sampling bias arising when testing populations do not equally represent user populations or when inappropriate performance metrics are used.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SelectionAndSamplingBias
AIO:DetectionBias,AIO:BiasSubset,,,Detection Bias,FALSE,0.46,"Systematic differences between groups in how outcomes are determined, potentially over- or underestimating effect size.","Systematic differences between groups in how outcomes are determined, potentially over- or underestimating effect size.",A selection and sampling bias characterized by systematic differences between groups in how outcomes are determined potentially over- or underestimating effect size.,A selection and sampling bias characterized by systematic differences between groups in how outcomes are determined potentially over- or underestimating effect size.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SelectionAndSamplingBias
AIO:PopulationBias,AIO:BiasSubset,,,Population Bias,FALSE,0.36,Systematic distortions in demographics or other user characteristics between represented users and the target population.,,A selection and sampling bias characterized by systematic distortions in demographics or other user characteristics between represented users and the target population.,A selection and sampling bias characterized by systematic distortions in demographics or other user characteristics between represented users and the target population.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SelectionAndSamplingBias
AIO:RepresentationBias,AIO:BiasSubset,,,Representation Bias,FALSE,0.41,"Bias due to non-random sampling of subgroups, making trends non-generalizable to new populations.","Bias due to non-random sampling of subgroups, making trends non-generalizable to new populations.",A selection and sampling bias due to non-random sampling of subgroups making trends non-generalizable to new populations.,A selection and sampling bias due to non-random sampling of subgroups making trends non-generalizable to new populations.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SelectionAndSamplingBias
AIO:UncertaintyBias,AIO:BiasSubset,,,Uncertainty Bias,FALSE,0.42,"Bias favoring groups better represented in training data, due to less prediction uncertainty.","Bias favoring groups better represented in training data, due to less prediction uncertainty.",A selection and sampling bias favoring groups better represented in training data due to less prediction uncertainty.,A selection and sampling bias favoring groups better represented in training data due to less prediction uncertainty.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SelectionAndSamplingBias
AIO:EcologicalFallacyBias,AIO:BiasSubset,Ecological Fallacy,,Ecological Fallacy Bias,FALSE,0.32,Bias occurring when an inference about an individual is made based on their group membership.,,A selection and sampling bias occurring when an inference about an individual is made based on their group membership.,A selection and sampling bias occurring when an inference about an individual is made based on their group membership.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SelectionAndSamplingBias
AIO:ExclusionBias,AIO:BiasSubset,,,Exclusion Bias,FALSE,0.28,Bias occurring when specific groups of user populations are excluded from testing and analysis.,,A selection and sampling bias occurring when specific groups of user populations are excluded from testing and analysis.,A selection and sampling bias occurring when specific groups of user populations are excluded from testing and analysis.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SelectionAndSamplingBias
AIO:PopularityBias,AIO:BiasSubset,,,Popularity Bias,FALSE,0.44,"Selection bias where more popular items are more exposed, under-representing less popular items.","Selection bias where more popular items are more exposed, under-representing less popular items.",A selection and sampling bias where more popular items are more exposed under-representing less popular items.,A selection and sampling bias where more popular items are more exposed under-representing less popular items.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SelectionAndSamplingBias
AIO:SimponsParadoxBias,AIO:BiasSubset,Simpson's Paradox,,Simpon's Paradox Bias,FALSE,#N/A,A statistical phenomenon where the association between two variables changes when controlling for another variable.,,A selection and sampling bias where the association between two variables changes when controlling for another variable.,A selection and sampling bias where the association between two variables changes when controlling for another variable.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:SelectionAndSamplingBias
AIO:Bias,AIO:BiasSubset,,,Bias,FALSE,0.18,Systematic error introduced into sampling or testing by selecting or encouraging one outcome or answer over others.,,A systematic error introduced into sampling or testing by selecting or encouraging one outcome or answer over others.,A systematic error introduced into sampling or testing by selecting or encouraging one outcome or answer over others.,https://www.merriam-webster.com/dictionary/bias,,,owl:Thing
AIO:ContentProductionBias,AIO:BiasSubset,,,Content Production Bias,FALSE,0.63,"Bias from structural, lexical, semantic, and syntactic differences in user-generated content.","Bias from structural, lexical, semantic, and syntactic differences in user-generated content.",A use and interpretation bias arising from structural lexical semantic and syntactic differences in user-generated content.,A use and interpretation bias arising from structural lexical semantic and syntactic differences in user-generated content.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:UseAndInterpretationBias
AIO:LinkingBias,AIO:BiasSubset,,,Linking Bias,FALSE,0.45,"Bias arising when network attributes obtained from user connections, activities, or interactions misrepresent true user behavior.","Bias arising when network attributes obtained from user connections, activities, or interactions misrepresent true user behavior.",A use and interpretation bias arising when network attributes obtained from user connections activities or interactions misrepresent true user behavior.,A use and interpretation bias arising when network attributes obtained from user connections activities or interactions misrepresent true user behavior.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:UseAndInterpretationBias
AIO:ConceptDriftBias,AIO:BiasSubset,Concept Drift,,Concept Drift Bias,FALSE,0.23,"Bias due to the use of a system outside its planned domain of application, causing performance gaps between laboratory settings and the real world.",,A use and interpretation bias due to the use of a system outside its planned domain of application causing performance gaps between laboratory settings and the real world.,A use and interpretation bias due to the use of a system outside its planned domain of application causing performance gaps between laboratory settings and the real world.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:UseAndInterpretationBias
AIO:FeedbackLoopBias,AIO:BiasSubset,,,Feedback Loop Bias,FALSE,0.25,Effects occurring when an algorithm learns from user behavior and feeds that behavior back into the model.,,A use and interpretation bias occurring when an algorithm learns from user behavior and feeds that behavior back into the model.,A use and interpretation bias occurring when an algorithm learns from user behavior and feeds that behavior back into the model.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:UseAndInterpretationBias
AIO:ActivityBias,AIO:BiasSubset,,,Activity Bias,FALSE,0.29,"Selection bias occurring when systems/platforms get training data from their most active users, rather than less active or inactive users.",,A use and interpretation bias occurring when systems/platforms get training data from their most active users rather than less active or inactive users.,A use and interpretation bias occurring when systems/platforms get training data from their most active users rather than less active or inactive users.,https://en.wikipedia.org/wiki/Interpretive_bias,,,AIO:UseAndInterpretationBias
AIO:EmergentBias,AIO:BiasSubset,,,Emergent Bias,FALSE,0.24,Bias resulting from the use and reliance on algorithms across new or unanticipated contexts.,,A use and interpretation bias resulting from the use and reliance on algorithms across new or unanticipated contexts.,A use and interpretation bias resulting from the use and reliance on algorithms across new or unanticipated contexts.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:UseAndInterpretationBias
AIO:HostileAttributionBias,AIO:BiasSubset,,,Hostile Attribution Bias,FALSE,0.40,Bias where individuals perceive benign or ambiguous behaviors as hostile.,Bias where individuals perceive benign or ambiguous behaviors as hostile.,A use and interpretation bias where individuals perceive benign or ambiguous behaviors as hostile.,A use and interpretation bias where individuals perceive benign or ambiguous behaviors as hostile.,https://en.wikipedia.org/wiki/Interpretive_bias,,,AIO:UseAndInterpretationBias
AIO:DataDredgingBias,AIO:BiasSubset,Data Dredging,,Data Dredging Bias,FALSE,0.22,Statistical bias where testing many hypotheses in a dataset may yield apparent statistical significance even when results are nonsignificant.,,A use and interpretation bias where testing many hypotheses in a dataset may yield apparent statistical significance even when results are nonsignificant.,A use and interpretation bias where testing many hypotheses in a dataset may yield apparent statistical significance even when results are nonsignificant.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:UseAndInterpretationBias
AIO:RankingBias,AIO:BiasSubset,,,Ranking Bias,FALSE,0.33,"The idea that top-ranked results are the most relevant and important, leading to more clicks than other results.",,An anchoring bias characterized by the idea that top-ranked results are the most relevant and important leading to more clicks than other results.,An anchoring bias characterized by the idea that top-ranked results are the most relevant and important leading to more clicks than other results.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:AnchoringBias
AIO:PresentationBias,AIO:BiasSubset,,,Presentation Bias,FALSE,0.36,"Bias arising from how information is presented on the Web, via a user interface, due to rating or ranking of output, or through users' self-selected, biased interaction.",,An individual bias arising from how information is presented on the Web via a user interface due to rating or ranking of output or through users' self-selected biased interaction.,An individual bias arising from how information is presented on the Web via a user interface due to rating or ranking of output or through users' self-selected biased interaction.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:UserInteractionBias,AIO:BiasSubset,,,User Interaction Bias,FALSE,0.45,"Bias arising when a user imposes their own biases during interaction with data, output, results, etc.","Bias arising when a user imposes their own biases during interaction with data, output, results, etc.",An individual bias arising when a user imposes their own biases during interaction with data output results etc.,An individual bias arising when a user imposes their own biases during interaction with data output results etc.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:ConsumerBias,AIO:BiasSubset,,,Consumer Bias,FALSE,0.20,"Bias arising when an algorithm or platform provides users a venue to express their biases, occurring from either side in a digital interaction.",,A bias arising when an algorithm or platform provides users a venue to express their biases occurring from either side in a digital interaction.,An individual bias arising when an algorithm or platform provides users a venue to express their biases occurring from either side in a digital interaction.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:AvailabilityHeuristicBias,AIO:BiasSubset,Availability Heuristic|Availability Bias,,Availability Heuristic Bias,FALSE,0.28,A mental shortcut where easily recalled information is overweighted in judgment and decision-making.,,A cognitive bias characterized by a mental shortcut where easily recalled information is overweighted in judgment and decision-making.,An individual bias characterized by a mental shortcut where easily recalled information is overweighted in judgment and decision-making.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:CognitiveBias,AIO:BiasSubset,,,Cognitive Bias,FALSE,0.29,"Systematic deviation from rational judgment and decision-making, including adaptive mental shortcuts known as heuristics.",,A systematic deviation from rational judgment and decision-making including adaptive mental shortcuts known as heuristics.,An individual bias characterized by deviations from rational judgment and decision-making including adaptive mental shortcuts known as heuristics.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:RashomonEffectBias,AIO:BiasSubset,Rashomon Effect|Rashomon Principle,,Rashomon Effect Bias,FALSE,0.54,"Differences in perspective, memory, recall, interpretation, and reporting of the same event by multiple persons or witnesses.","Differences in perspective, memory, recall, interpretation, and reporting of the same event by multiple persons or witnesses.",An individual bias characterized by differences in perspective memory recall interpretation and reporting of the same event by multiple persons or witnesses.,An individual bias characterized by differences in perspective memory recall interpretation and reporting of the same event by multiple persons or witnesses.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:AutomationComplacencyBias,AIO:BiasSubset,Automation Complaceny,,Automation Complacency Bias,FALSE,0.73,"Over-reliance on automated systems, leading to attenuated human skills, such as with spelling and autocorrect.","Over-reliance on automated systems, leading to attenuated human skills, such as with spelling and autocorrect.",A bias characterized by over-reliance on automated systems leading to attenuated human skills.,An individual bias characterized by over-reliance on automated systems leading to attenuated human skills.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:BehavioralBias,AIO:BiasSubset,,,Behavioral Bias,FALSE,0.45,"Systematic distortions in user behavior across platforms or contexts, or across users represented in different datasets.","Systematic distortions in user behavior across platforms or contexts, or across users represented in different datasets.",An individual bias characterized by systematic distortions in user behavior across platforms or contexts or across users represented in different datasets.,An individual bias characterized by systematic distortions in user behavior across platforms or contexts or across users represented in different datasets.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:AnchoringBias,AIO:BiasSubset,,,Anchoring Bias,FALSE,0.38,"The influence of a reference point or anchor on decisions, leading to insufficient adjustment from that anchor point.",,A cognitive bias characterized by the influence of a reference point or anchor on decisions leading to insufficient adjustment from that anchor point.,An individual bias characterized by the influence of a reference point or anchor on decisions leading to insufficient adjustment from that anchor point.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:ConfirmationBias,AIO:BiasSubset,,,Confirmation Bias,FALSE,0.42,"The tendency to prefer information that confirms existing beliefs, influencing the search for, interpretation of, and recall of information.","The tendency to prefer information that confirms existing beliefs, influencing the search for, interpretation of, and recall of information.",A cognitive bias characterized by the tendency to prefer information that confirms existing beliefs influencing the search for interpretation of and recall of information.,An individual bias characterized by the tendency to prefer information that confirms existing beliefs influencing the search for interpretation of and recall of information.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:SelectiveAdherenceBias,AIO:BiasSubset,,,Selective Adherence Bias,FALSE,0.37,The tendency to selectively adopt algorithmic advice that matches pre-existing beliefs and stereotypes.,,An individual bias characterized by the tendency to selectively adopt algorithmic advice that matches pre-existing beliefs and stereotypes.,An individual bias characterized by the tendency to selectively adopt algorithmic advice that matches pre-existing beliefs and stereotypes.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:ImplicitBias,AIO:BiasSubset,Confirmatory Bias,,Implicit Bias,FALSE,0.73,"Unconscious beliefs, attitudes, feelings, associations, or stereotypes that affect information processing, decision-making, and actions.","Unconscious beliefs, attitudes, feelings, associations, or stereotypes that affect information processing, decision-making, and actions.",An individual bias characterized by unconscious beliefs attitudes feelings associations or stereotypes that affect information processing decision-making and actions.,An individual bias characterized by unconscious beliefs attitudes feelings associations or stereotypes that affect information processing decision-making and actions.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:LossOfSituationalAwarenessBias,AIO:BiasSubset,,,Loss Of Situational Awareness Bias,FALSE,0.33,"When automation leads to humans being unaware of their situation, making them unprepared to assume control in cooperative systems.",,An individual bias occurring when automation leads to humans being unaware of their situation making them unprepared to assume control in cooperative systems.,An individual bias occurring when automation leads to humans being unaware of their situation making them unprepared to assume control in cooperative systems.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:ModeConfusionBias,AIO:BiasSubset,,,Mode Confusion Bias,FALSE,0.30,"When modal interfaces confuse human operators, causing actions appropriate for a different mode but incorrect for the current situation.",,A bias occurring when modal interfaces confuse human operators causing actions appropriate for a different mode but incorrect for the current situation.,An individual bias occurring when modal interfaces confuse human operators causing actions appropriate for a different mode but incorrect for the current situation.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:AnnotatorReportingBias,AIO:BiasSubset,,,Annotator Reporting Bias,FALSE,0.29,When users rely on automation as a heuristic replacement for their own information seeking and processing.,,An individual bias occurring when users rely on automation as a heuristic replacement for their own information seeking and processing.,An individual bias occurring when users rely on automation as a heuristic replacement for their own information seeking and processing.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:HumanReportingBias,AIO:BiasSubset,,,Human Reporting Bias,FALSE,0.29,When users rely on automation as a heuristic replacement for their own information seeking and processing.,,An individual bias that arises when users depend on automated systems as heuristic substitutes for their own information-seeking and processing efforts.,An individual bias that arises when users depend on automated systems as heuristic substitutes for their own information-seeking and processing efforts.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:StreetlightEffectBias,AIO:BiasSubset,Streetlight Effect,,Streetlight Effect Bias,FALSE,0.31,Bias where people search only where it is easiest to look.,,An individual bias where people search only where it is easiest to look.,An individual bias where people search only where it is easiest to look.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:InterpretationBias,AIO:BiasSubset,,,Interpretation Bias,FALSE,0.35,A form of information processing bias where users interpret algorithmic outputs according to their internalized biases and views.,,An individual bias where users interpret algorithmic outputs according to their internalized biases and views.,An individual bias where users interpret algorithmic outputs according to their internalized biases and views.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:IndividualBias
AIO:MathematicalFunction,AIO:ClassSubset,,,Mathematical Function,FALSE,#N/A,A mathematical rule that gives the value of a dependent variable corresponding to specified values of one or more independent variables.,,#N/A,A mathematical rule that gives the value of a dependent variable corresponding to specified values of one or more independent variables.,https://www.sciencedirect.com/topics/mathematics/mathematical-function,,,owl:Thing
AIO:Layer,AIO:ClassSubset,,,Layer,FALSE,0.00,A structure or network topology in a deep learning model that takes information from previous layers and passes it to the next layer.,,A structure or network topology in a deep learning model that takes information from previous layers and passes it to the next layer.,A structure or network topology in a deep learning model that takes information from previous layers and passes it to the next layer.,https://en.wikipedia.org/wiki/Layer_(deep_learning),,,owl:Thing
AIO:Network,AIO:ClassSubset,,,Network,FALSE,0.29,"A system of interconnected nodes or entities for communication, computation, or data exchange.",,A system of interconnected nodes or entities for communication computation or data exchange.,"A system of interconnected nodes or entities for communication, computation or data exchange.",,,,owl:Thing
AIO:ExponentialFunction,AIO:FunctionSubset,,,Exponential Function,FALSE,0.47,The exponential function is a mathematical function denoted by f(x)=exp or e^{x}.,The exponential function is a mathematical function denoted by f(x)=exp or e^{x}.,An activation function that is the mathematical function denoted by f(x)=exp or e^{x}.,A mathematical function denoted by f(x)=exp or e^{x}.,https://www.tensorflow.org/api_docs/python/tf/keras/activations/exponential,,,AIO:MathematicalFunction
AIO:GELUFunction,AIO:FunctionSubset,Gaussian Error Linear Unit|GELU,,GELU Function,FALSE,0.58,"Gaussian error linear unit (GELU) computes x * P(X <= x), where P(X) ~ N(0, 1). The (GELU) nonlinearity weights inputs by their value, rather than gates inputs by their sign as in ReLU.","Gaussian error linear unit (GELU) computes x * P(X <= x), where P(X) ~ N(0, 1). The (GELU) nonlinearity weights inputs by their value, rather than gates inputs by their sign as in ReLU.",An activation function that computes x * P(X <= x) where P(X) ~ N(0 1) weighting inputs by their value rather than gating inputs by their sign as in ReLU.,A mathematical function that computes x * P(X <= x) where P(X) ~ N(0 1) weighting inputs by their value rather than gating inputs by their sign as in ReLU.,https://www.tensorflow.org/api_docs/python/tf/keras/activations/gelu,,,AIO:MathematicalFunction
AIO:HardSigmoidFunction,AIO:FunctionSubset,,,Hard Sigmoid Function,FALSE,0.71,A faster approximation of the sigmoid activation. Piecewise linear approximation of the sigmoid function. Ref: 'https://en.wikipedia.org/wiki/Hard_sigmoid',A faster approximation of the sigmoid activation. Piecewise linear approximation of the sigmoid function. Ref: 'https://en.wikipedia.org/wiki/Hard_sigmoid',An activation function that is a faster approximation of the sigmoid activation using a piecewise linear approximation.,A mathematical function that is a faster approximation of the sigmoid activation using a piecewise linear approximation.,https://www.tensorflow.org/api_docs/python/tf/keras/activations/hard_sigmoid,,,AIO:MathematicalFunction
AIO:SoftmaxFunction,AIO:FunctionSubset|AIO:ActivationFunctionSubset,,,Softmax Function,FALSE,0.70,"The elements of the output vector are in range (0, 1) and sum to 1. Each vector is handled independently. The axis argument sets which axis of the input the function is applied along. Softmax is often used as the activation for the last layer of a classification network because the result could be interpreted as a probability distribution. The softmax of each vector x is computed as exp(x) / tf.reduce_sum(exp(x)). The input values in are the log-odds of the resulting probability.","The elements of the output vector are in range (0, 1) and sum to 1. Each vector is handled independently. The axis argument sets which axis of the input the function is applied along. Softmax is often used as the activation for the last layer of a classification network because the result could be interpreted as a probability distribution. The softmax of each vector x is computed as exp(x) / tf.reduce_sum(exp(x)). The input values in are the log-odds of the resulting probability.",An activation function where the elements of the output vector are in range (0 1) and sum to 1 and each vector is handled independently.,A mathematical function where the elements of the output vector are in range (0 1) and sum to 1 and each vector is handled independently.,https://www.tensorflow.org/api_docs/python/tf/keras/activations/softmax,,,AIO:MathematicalFunction
AIO:SigmoidFunction,AIO:FunctionSubset|AIO:ActivationFunctionSubset,tore,,Sigmoid Function,FALSE,0.66,"Applies the sigmoid activation function sigmoid(x) = 1 / (1 + exp(-x)). For small values (<-5), sigmoid returns a value close to zero, and for large values (>5) the result of the function gets close to 1. Sigmoid is equivalent to a 2-element Softmax, where the second element is assumed to be zero. The sigmoid function always returns a value between 0 and 1.","Applies the sigmoid activation function sigmoid(x) = 1 / (1 + exp(-x)). For small values (<-5), sigmoid returns a value close to zero, and for large values (>5) the result of the function gets close to 1. Sigmoid is equivalent to a 2-element Softmax, where the second element is assumed to be zero. The sigmoid function always returns a value between 0 and 1.",An activation function that applies the sigmoid activation function sigmoid(x) = 1 / (1 + exp(-x)) always returning a value between 0 and 1.,A mathematical function that applies the sigmoid activation function sigmoid(x) = 1 / (1 + exp(-x)) always returning a value between 0 and 1.,https://www.tensorflow.org/api_docs/python/tf/keras/activations/sigmoid,,,AIO:MathematicalFunction
AIO:LinearFunction,AIO:FunctionSubset|AIO:ActivationFunctionSubset,,,Linear Function,FALSE,0.36,A linear function has the form f(x) = a + bx.,,An activation function that has the form f(x) = a + bx.,A mathematical function that has the form f(x) = a + bx.,https://www.tensorflow.org/api_docs/python/tf/keras/activations/linear,,,AIO:MathematicalFunction
AIO:SoftplusFunction,AIO:FunctionSubset|AIO:ActivationFunctionSubset,,,Softplus Function,FALSE,0.64,softplus(x) = log(exp(x) + 1),softplus(x) = log(exp(x) + 1),An activation function that is softplus(x) = log(exp(x) + 1).,A mathematical function that is softplus(x) = log(exp(x) + 1).,https://www.tensorflow.org/api_docs/python/tf/keras/activations/softplus,,,AIO:MathematicalFunction
AIO:SoftsignFunction,AIO:FunctionSubset|AIO:ActivationFunctionSubset,,,Softsign Function,FALSE,0.54,softsign(x) = x / (abs(x) + 1),softsign(x) = x / (abs(x) + 1),An activation function that is softsign(x) = x / (abs(x) + 1).,A mathematical function that is softsign(x) = x / (abs(x) + 1).,https://www.tensorflow.org/api_docs/python/tf/keras/activations/softsign,,,AIO:MathematicalFunction
AIO:TanhFunction,AIO:FunctionSubset|AIO:ActivationFunctionSubset,hyperbolic tangent,,Tanh Function,FALSE,0.70,Hyperbolic tangent activation function.,Hyperbolic tangent activation function.,An activation function that is the hyperbolic tangent activation function.,A mathematical function that is the hyperbolic tangent activation function.,https://www.tensorflow.org/api_docs/python/tf/keras/activations/tanh,,,AIO:MathematicalFunction
AIO:ELUFunction,AIO:FunctionSubset|AIO:ActivationFunctionSubset,Exponential Linear Unit|ELU,,ELU Function,FALSE,0.68,The exponential linear unit (ELU) with alpha > 0 is: x if x > 0 and alpha * (exp(x) - 1) if x < 0 The ELU hyperparameter alpha controls the value to which an ELU saturates for negative net inputs. ELUs diminish the vanishing gradient effect. ELUs have negative values which pushes the mean of the activations closer to zero. Mean activations that are closer to zero enable faster Learning as they bring the gradient closer to the natural gradient. ELUs saturate to a negative value when the argument gets smaller. Saturation means a small derivative which decreases the variation and the information that is propagated to the next layer.,The exponential linear unit (ELU) with alpha > 0 is: x if x > 0 and alpha * (exp(x) - 1) if x < 0 The ELU hyperparameter alpha controls the value to which an ELU saturates for negative net inputs. ELUs diminish the vanishing gradient effect. ELUs have negative values which pushes the mean of the activations closer to zero. Mean activations that are closer to zero enable faster Learning as they bring the gradient closer to the natural gradient. ELUs saturate to a negative value when the argument gets smaller. Saturation means a small derivative which decreases the variation and the information that is propagated to the next layer.,An activation function that is x if x > 0 and alpha * (exp(x) - 1) if x < 0 where alpha controls the value to which an ELU saturates for negative net inputs.,A mathematical function that is x if x > 0 and alpha * (exp(x) - 1) if x < 0 where alpha controls the value to which an ELU saturates for negative net inputs.,https://www.tensorflow.org/api_docs/python/tf/keras/activations/elu,,,AIO:MathematicalFunction
AIO:SwishFunction,AIO:FunctionSubset|AIO:ActivationFunctionSubset,,,Swish Function,FALSE,0.56,"x*sigmoid(x). It is a smooth, non-monotonic function that consistently matches or outperforms ReLU on deep networks, it is unbounded above and bounded below.","x*sigmoid(x). It is a smooth, non-monotonic function that consistently matches or outperforms ReLU on deep networks, it is unbounded above and bounded below.",An activation function that is x*sigmoid(x) a smooth non-monotonic function that consistently matches or outperforms ReLU on deep networks.,A mathematical function that is x*sigmoid(x) a smooth non-monotonic function that consistently matches or outperforms ReLU on deep networks.,https://www.tensorflow.org/api_docs/python/tf/keras/activations/swish,,,AIO:MathematicalFunction
AIO:SELUFunction,AIO:FunctionSubset|AIO:ActivationFunctionSubset,Scaled Exponential Linear Unit|SELU,,SELU Function,FALSE,0.16,The SELU activation function multiplies scale (> 1) with the output of the ELU function to ensure a slope larger than one for positive inputs.,,An activation function that multiplies scale (> 1) with the output of the ELU function to ensure a slope larger than one for positive inputs.,A mathematical function that multiplies scale (> 1) with the output of the ELU function to ensure a slope larger than one for positive inputs.,https://www.tensorflow.org/api_docs/python/tf/keras/activations/selu,,,AIO:MathematicalFunction
AIO:ReLUFunction,AIO:FunctionSubset|AIO:ActivationFunctionSubset,Rectified Linear Unit|ReLU,,ReLU Function,FALSE,0.50,"The ReLU activation function returns: max(x, 0), the element-wise maximum of 0 and the input tensor.","The ReLU activation function returns: max(x, 0), the element-wise maximum of 0 and the input tensor.",An activation function that returns max(x 0) the element-wise maximum of 0 and the input tensor.,A mathematical function that returns max(x 0) the element-wise maximum of 0 and the input tensor.,https://www.tensorflow.org/api_docs/python/tf/keras/activations/relu,,,AIO:MathematicalFunction
AIO:BatchNorm1DLayer,AIO:LayerSubset,BatchNorm1D|BatchNorm1D|BatchNorm1D,,BatchNorm1D Layer,FALSE,0.78,Applies Batch Normalization over a 2D or 3D input as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .,Applies Batch Normalization over a 2D or 3D input as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .,A batch normalization layer that applies Batch Normalization over a 2D or 3D input.,A batch normalization layer that applies Batch Normalization over a 2D or 3D input.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:BatchNormalizationLayer
AIO:BatchNorm2DLayer,AIO:LayerSubset,BatchNorm2D|BatchNorm2D|BatchNorm2D,,BatchNorm2D Layer,FALSE,0.87,Applies Batch Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension) as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .,Applies Batch Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension) as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .,A batch normalization layer that applies Batch Normalization over a 4D input.,A batch normalization layer that applies Batch Normalization over a 4D input.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:BatchNormalizationLayer
AIO:BatchNorm3DLayer,AIO:LayerSubset,BatchNorm3D|BatchNorm3D|BatchNorm3D,,BatchNorm3D Layer,FALSE,0.87,Applies Batch Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension) as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .,Applies Batch Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension) as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .,A batch normalization layer that applies Batch Normalization over a 5D input.,A batch normalization layer that applies Batch Normalization over a 5D input.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:BatchNormalizationLayer
AIO:SyncBatchNormLayer,AIO:LayerSubset,SyncBatchNorm|SyncBatchNorm,,SyncBatchNorm Layer,FALSE,0.95,Applies Batch Normalization over a N-Dimensional input (a mini-batch of [N-2]D inputs with additional channel dimension) as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .,Applies Batch Normalization over a N-Dimensional input (a mini-batch of [N-2]D inputs with additional channel dimension) as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .,A batch normalization layer that applies synchronous Batch Normalization across multiple devices.,A batch normalization layer that applies synchronous Batch Normalization across multiple devices.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:BatchNormalizationLayer
AIO:LazyBatchNorm1DLayer,AIO:LayerSubset,LazyBatchNorm1D|LazyBatchNorm1D|LazyBatchNorm1D,,LazyBatchNorm1D Layer,FALSE,0.77,A torch.nn.BatchNorm1D module with lazy initialization of the num_features argument of the BatchNorm1D that is inferred from the input.size(1).,A torch.nn.BatchNorm1D module with lazy initialization of the num_features argument of the BatchNorm1D that is inferred from the input.size(1).,A batch normalization layer that lazily initializes the num_features argument from the input size for 1D data.,A batch normalization layer that lazily initializes the num_features argument from the input size for 1D data.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:BatchNormalizationLayer
AIO:LazyBatchNorm2DLayer,AIO:LayerSubset,LazyBatchNorm2D|LazyBatchNorm2D|LazyBatchNorm2D,,LazyBatchNorm2D Layer,FALSE,0.77,A torch.nn.BatchNorm2D module with lazy initialization of the num_features argument of the BatchNorm2D that is inferred from the input.size(1).,A torch.nn.BatchNorm2D module with lazy initialization of the num_features argument of the BatchNorm2D that is inferred from the input.size(1).,A batch normalization layer that lazily initializes the num_features argument from the input size for 2D data.,A batch normalization layer that lazily initializes the num_features argument from the input size for 2D data.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:BatchNormalizationLayer
AIO:LazyBatchNorm3DLayer,AIO:LayerSubset,LazyBatchNorm3D|LazyBatchNorm3D|LazyBatchNorm3D,,LazyBatchNorm3D Layer,FALSE,0.77,A torch.nn.BatchNorm3D module with lazy initialization of the num_features argument of the BatchNorm3D that is inferred from the input.size(1).,A torch.nn.BatchNorm3D module with lazy initialization of the num_features argument of the BatchNorm3D that is inferred from the input.size(1).,A batch normalization layer that lazily initializes the num_features argument from the input size for 3D data.,A batch normalization layer that lazily initializes the num_features argument from the input size for 3D data.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:BatchNormalizationLayer
AIO:CategoryEncodingLayer,AIO:LayerSubset,,,CategoryEncoding Layer,FALSE,0.78,"A preprocessing layer which encodes integer features. This layer provides options for condensing data into a categorical encoding when the total number of tokens are known in advance. It accepts integer values as inputs, and it outputs a dense or sparse representation of those inputs. For integer inputs where the total number of tokens is not known, use tf.keras.layers.IntegerLookup instead.","A preprocessing layer which encodes integer features. This layer provides options for condensing data into a categorical encoding when the total number of tokens are known in advance. It accepts integer values as inputs, and it outputs a dense or sparse representation of those inputs. For integer inputs where the total number of tokens is not known, use tf.keras.layers.IntegerLookup instead.",A categorical features preprocessing layer that encodes integer features providing options for condensing data into a categorical encoding.,A categorical features preprocessing layer that encodes integer features providing options for condensing data into a categorical encoding.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/CategoryEncoding,,,AIO:CategoricalFeaturesPreprocessingLayer
AIO:IntegerLookupLayer,AIO:LayerSubset,,,IntegerLookup Layer,FALSE,0.25,A preprocessing layer which maps integer features to contiguous ranges.,,A categorical features preprocessing layer that maps integer features to contiguous ranges.,A categorical features preprocessing layer that maps integer features to contiguous ranges.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/IntegerLookup,,,AIO:CategoricalFeaturesPreprocessingLayer
AIO:StringLookupLayer,AIO:LayerSubset,,,StringLookup Layer,FALSE,0.25,A preprocessing layer which maps string features to integer indices.,,A categorical features preprocessing layer that maps string features to integer indices.,A categorical features preprocessing layer that maps string features to integer indices.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/StringLookup,,,AIO:CategoricalFeaturesPreprocessingLayer
AIO:HashingLayer,AIO:LayerSubset,,,Hashing Layer,FALSE,0.89,"A preprocessing layer which hashes and bins categorical features. This layer transforms categorical inputs to hashed output. It element-wise converts a ints or strings to ints in a fixed range. The stable hash function uses tensorflow::ops::Fingerprint to produce the same output consistently across all platforms. This layer uses FarmHash64 by default, which provides a consistent hashed output across different platforms and is stable across invocations, regardless of device and context, by mixing the input bits thoroughly. If you want to obfuscate the hashed output, you can also pass a random salt argument in the constructor. In that case, the layer will use the SipHash64 hash function, with the salt value serving as additional input to the hash function.","A preprocessing layer which hashes and bins categorical features. This layer transforms categorical inputs to hashed output. It element-wise converts a ints or strings to ints in a fixed range. The stable hash function uses tensorflow::ops::Fingerprint to produce the same output consistently across all platforms. This layer uses FarmHash64 by default, which provides a consistent hashed output across different platforms and is stable across invocations, regardless of device and context, by mixing the input bits thoroughly. If you want to obfuscate the hashed output, you can also pass a random salt argument in the constructor. In that case, the layer will use the SipHash64 hash function, with the salt value serving as additional input to the hash function.",A categorical features preprocessing layer which hashes and bins categorical features.,A categorical features preprocessing layer which hashes and bins categorical features.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Hashing,,,AIO:CategoricalFeaturesPreprocessingLayer
AIO:Convolution1DLayer,AIO:LayerSubset,Conv1D Layer|nn.Conv1D|Conv1D|Convolution1D|Convolution1D,,Convolution1D Layer,FALSE,0.33,1D convolution layer (e.g. temporal convolution).,,A layer that implements 1D convolution (e.g. temporal convolution).,A convolutional layer that implements 1D convolution (e.g. temporal convolution).,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv1D,,,AIO:ConvolutionalLayer
AIO:Convolution2DLayer,AIO:LayerSubset,Conv2D Layer|nn.Conv2D|Conv2D|Convolution2D|Convolution2D,,Convolution2D Layer,FALSE,0.90,"2D convolution layer (e.g. spatial convolution over images). This layer creates a convolution kernel that is convolved with the layer input to produce a tensor of outputs. If use_bias is True, a bias vector is created and added to the outputs. Finally, if activation is not None, it is applied to the outputs as well. When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers or None, does not include the sample axis), e.g. input_shape=(128, 128, 3) for 128x128 RGB pictures in data_format=""channels_last"". You can use None when a dimension has variable size.","2D convolution layer (e.g. spatial convolution over images). This layer creates a convolution kernel that is convolved with the layer input to produce a tensor of outputs. If use_bias is True, a bias vector is created and added to the outputs. Finally, if activation is not None, it is applied to the outputs as well. When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers or None, does not include the sample axis), e.g. input_shape=(128, 128, 3) for 128x128 RGB pictures in data_format=""channels_last"". You can use None when a dimension has variable size.",A layer that implements 2D convolution (e.g. spatial convolution over images).,A convolutional layer that implements 2D convolution (e.g. spatial convolution over images).,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2D,,,AIO:ConvolutionalLayer
AIO:Convolution3DLayer,AIO:LayerSubset,Conv3D Layer|nn.Conv3D|Conv3D|Convolution3D|Convolution3D,,Convolution3D Layer,FALSE,0.88,"3D convolution layer (e.g. spatial convolution over volumes). This layer creates a convolution kernel that is convolved with the layer input to produce a tensor of outputs. If use_bias is True, a bias vector is created and added to the outputs. Finally, if activation is not None, it is applied to the outputs as well. When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers or None, does not include the sample axis), e.g. input_shape=(128, 128, 128, 1) for 128x128x128 volumes with a single channel, in data_format=""channels_last"".","3D convolution layer (e.g. spatial convolution over volumes). This layer creates a convolution kernel that is convolved with the layer input to produce a tensor of outputs. If use_bias is True, a bias vector is created and added to the outputs. Finally, if activation is not None, it is applied to the outputs as well. When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers or None, does not include the sample axis), e.g. input_shape=(128, 128, 128, 1) for 128x128x128 volumes with a single channel, in data_format=""channels_last"".",A layer that implements 3D convolution (e.g. spatial convolution over volumes).,A convolutional layer that implements 3D convolution (e.g. spatial convolution over volumes).,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv3D,,,AIO:ConvolutionalLayer
AIO:ConvLSTM1DLayer,AIO:LayerSubset,,,ConvLSTM1D Layer,FALSE,0.65,"1D Convolutional LSTM. Similar to an LSTM layer, but the input transformations and recurrent transformations are both convolutional.","1D Convolutional LSTM. Similar to an LSTM layer, but the input transformations and recurrent transformations are both convolutional.",A convolutional layer that implements a 1D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations.,A convolutional layer that implements a 1D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/ConvLSTM1D,,,AIO:ConvolutionalLayer
AIO:ConvLSTM2DLayer,AIO:LayerSubset,,,ConvLSTM2D Layer,FALSE,0.65,"2D Convolutional LSTM. Similar to an LSTM layer, but the input transformations and recurrent transformations are both convolutional.","2D Convolutional LSTM. Similar to an LSTM layer, but the input transformations and recurrent transformations are both convolutional.",A convolutional layer that implements a 2D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations.,A convolutional layer that implements a 2D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/ConvLSTM2D,,,AIO:ConvolutionalLayer
AIO:ConvLSTM3DLayer,AIO:LayerSubset,,,ConvLSTM3D Layer,FALSE,0.65,"3D Convolutional LSTM. Similar to an LSTM layer, but the input transformations and recurrent transformations are both convolutional.","3D Convolutional LSTM. Similar to an LSTM layer, but the input transformations and recurrent transformations are both convolutional.",A convolutional layer that implements a 3D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations.,A convolutional layer that implements a 3D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/ConvLSTM3D,,,AIO:ConvolutionalLayer
AIO:Convolution1DTransposeLayer,AIO:LayerSubset,Conv1DTranspose Layer|nn.ConvTranspose1D|ConvTranspose1D|Convolution1DTranspose|Convolution1DTranspose,,Convolution1DTranspose Layer,FALSE,0.94,"Transposed convolution layer (sometimes called Deconvolution). The need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of a normal convolution, i.e., from something that has the shape of the output of some convolution to something that has the shape of its input while maintaining a connectivity pattern that is compatible with said convolution. When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers or None, does not include the sample axis), e.g. input_shape=(128, 3) for data with 128 time steps and 3 channels.","Transposed convolution layer (sometimes called Deconvolution). The need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of a normal convolution, i.e., from something that has the shape of the output of some convolution to something that has the shape of its input while maintaining a connectivity pattern that is compatible with said convolution. When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers or None, does not include the sample axis), e.g. input_shape=(128, 3) for data with 128 time steps and 3 channels.",A layer that implements transposed 1D convolution sometimes called deconvolution.,A convolutional layer that implements transposed 1D convolution sometimes called deconvolution.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv1DTranspose,,,AIO:ConvolutionalLayer
AIO:Convolution2DTransposeLayer,AIO:LayerSubset,Conv2DTranspose Layer|nn.ConvTranspose2D|ConvTranspose2D|Convolution2DTranspose|Convolution2DTranspose,,Convolution2DTranspose Layer,FALSE,0.82,Transposed convolution layer (sometimes called Deconvolution).,Transposed convolution layer (sometimes called Deconvolution).,A layer that implements transposed 2D convolution,A convolutional layer that implements transposed 2D convolution,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2DTranspose,,,AIO:ConvolutionalLayer
AIO:Convolution3DTransposeLayer,AIO:LayerSubset,Conv3DTranspose Layer|nn.ConvTranspose3D|ConvTranspose3D|Convolution3DTranspose|Convolution3DTranspose,,Convolution3DTranspose Layer,FALSE,0.95,"Transposed convolution layer (sometimes called Deconvolution). The need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of a normal convolution, i.e., from something that has the shape of the output of some convolution to something that has the shape of its input while maintaining a connectivity pattern that is compatible with said convolution. When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers or None, does not include the sample axis), e.g. input_shape=(128, 128, 128, 3) for a 128x128x128 volume with 3 channels if data_format=""channels_last"".","Transposed convolution layer (sometimes called Deconvolution). The need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of a normal convolution, i.e., from something that has the shape of the output of some convolution to something that has the shape of its input while maintaining a connectivity pattern that is compatible with said convolution. When using this layer as the first layer in a model, provide the keyword argument input_shape (tuple of integers or None, does not include the sample axis), e.g. input_shape=(128, 128, 128, 3) for a 128x128x128 volume with 3 channels if data_format=""channels_last"".",A layer that implements transposed 3D convolution,A convolutional layer that implements transposed 3D convolution,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv3DTranspose,,,AIO:ConvolutionalLayer
AIO:DepthwiseConv1DLayer,AIO:LayerSubset,,,DepthwiseConv1D Layer,FALSE,0.95,"Depthwise 1D convolution. Depthwise convolution is a type of convolution in which each input channel is convolved with a different kernel (called a depthwise kernel). You can understand depthwise convolution as the first step in a depthwise separable convolution. It is implemented via the following steps: Split the input into individual channels. Convolve each channel with an individual depthwise kernel with depth_multiplier output channels. Concatenate the convolved outputs along the channels axis. Unlike a regular 1D convolution, depthwise convolution does not mix information across different input channels. The depth_multiplier argument determines how many filter are applied to one input channel. As such, it controls the amount of output channels that are generated per input channel in the depthwise step.","Depthwise 1D convolution. Depthwise convolution is a type of convolution in which each input channel is convolved with a different kernel (called a depthwise kernel). You can understand depthwise convolution as the first step in a depthwise separable convolution. It is implemented via the following steps: Split the input into individual channels. Convolve each channel with an individual depthwise kernel with depth_multiplier output channels. Concatenate the convolved outputs along the channels axis. Unlike a regular 1D convolution, depthwise convolution does not mix information across different input channels. The depth_multiplier argument determines how many filter are applied to one input channel. As such, it controls the amount of output channels that are generated per input channel in the depthwise step.",A layer that performs depthwise 1D convolution,A convolutional layer that performs depthwise 1D convolution,https://www.tensorflow.org/api_docs/python/tf/keras/layers/DepthwiseConv1D,,,AIO:ConvolutionalLayer
AIO:DepthwiseConv2DLayer,AIO:LayerSubset,,,DepthwiseConv2D Layer,FALSE,0.89,Depthwise 2D convolution.,Depthwise 2D convolution.,A layer that performs depthwise 2D convolution,A convolutional layer that performs depthwise 2D convolution,https://www.tensorflow.org/api_docs/python/tf/keras/layers/DepthwiseConv2D,,,AIO:ConvolutionalLayer
AIO:SeparableConvolution1DLayer,AIO:LayerSubset,SeparableConv1D Layer,,SeparableConvolution1D Layer,FALSE,0.84,"Depthwise separable 1D convolution. This layer performs a depthwise convolution that acts separately on channels, followed by a pointwise convolution that mixes channels. If use_bias is True and a bias initializer is provided, it adds a bias vector to the output. It then optionally applies an activation function to produce the final output.a","Depthwise separable 1D convolution. This layer performs a depthwise convolution that acts separately on channels, followed by a pointwise convolution that mixes channels. If use_bias is True and a bias initializer is provided, it adds a bias vector to the output. It then optionally applies an activation function to produce the final output.a",A layer that performs depthwise separable 1D convolution.,A convolutional layer that performs depthwise separable 1D convolution.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/SeparableConv1D,,,AIO:ConvolutionalLayer
AIO:SeparableConvolution2DLayer,AIO:LayerSubset,SeparableConv2D Layer,,SeparableConvolution2D Layer,FALSE,0.94,"Depthwise separable 2D convolution. Separable convolutions consist of first performing a depthwise spatial convolution (which acts on each input channel separately) followed by a pointwise convolution which mixes the resulting output channels. The depth_multiplier argument controls how many output channels are generated per input channel in the depthwise step. Intuitively, separable convolutions can be understood as a way to factorize a convolution kernel into two smaller kernels, or as an extreme version of an Inception block.","Depthwise separable 2D convolution. Separable convolutions consist of first performing a depthwise spatial convolution (which acts on each input channel separately) followed by a pointwise convolution which mixes the resulting output channels. The depth_multiplier argument controls how many output channels are generated per input channel in the depthwise step. Intuitively, separable convolutions can be understood as a way to factorize a convolution kernel into two smaller kernels, or as an extreme version of an Inception block.",A layer that performs depthwise separable 2D convolution.,A convolutional layer that performs depthwise separable 2D convolution.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/SeparableConv2D,,,AIO:ConvolutionalLayer
AIO:ProbabilisticHiddenLayer,AIO:LayerSubset,,,Probabilistic Hidden Layer,FALSE,#N/A,,,A hidden layer that estimates the probability of a sample being within a certain category.,A hidden layer that estimates the probability of a sample being within a certain category.,,,,AIO:HiddenLayer
AIO:SpikingHiddenLayer,AIO:LayerSubset,,,Spiking Hidden Layer,FALSE,#N/A,,,"A hidden layer that makes connections to an additional, heterogeneous hidden layer; modeled after biological neural networks.","A hidden layer that makes connections to an additional, heterogeneous hidden layer; modeled after biological neural networks.",https://doi.org/10.1016/S0893-6080(97)00011-7,,,AIO:HiddenLayer
AIO:InputLayer,AIO:LayerSubset,,,Input Layer,FALSE,0.52,"The input layer of a neural network is composed of artificial input neurons, and brings the initial data into the system for further processing by subsequent layers of artificial neurons. The input layer is the very beginning of the workflow for the artificial neural network.","The input layer of a neural network is composed of artificial input neurons, and brings the initial data into the system for further processing by subsequent layers of artificial neurons. The input layer is the very beginning of the workflow for the artificial neural network.",A layer composed of artificial input neurons that brings the initial data into the system for further processing by subsequent layers.,A layer composed of artificial input neurons that brings the initial data into the system for further processing by subsequent layers.,https://www.techopedia.com/definition/33262/input-layer-neural-networks,,,AIO:Layer
AIO:RecurrentLayer,AIO:LayerSubset,,,Recurrent Layer,FALSE,0.37,"A layer of an RNB, composed of recurrent units and with the number of which is the hidden size of the layer.",,A layer composed of recurrent units with the number equal to the hidden size of the layer.,A layer composed of recurrent units with the number equal to the hidden size of the layer.,https://docs.nvidia.com/deepLearning/performance/dl-performance-recurrent/index.html#recurrent-layer,,,AIO:Layer
AIO:OutputLayer,AIO:LayerSubset,,,Output Layer,FALSE,0.71,"The output layer in an artificial neural network is the last layer of neurons that produces given outputs for the program. Though they are made much like other artificial neurons in the neural network, output layer neurons may be built or observed in a different way, given that they are the last “actor” nodes on the network.","The output layer in an artificial neural network is the last layer of neurons that produces given outputs for the program. Though they are made much like other artificial neurons in the neural network, output layer neurons may be built or observed in a different way, given that they are the last “actor” nodes on the network.",A layer containing the last neurons in the network that produces given outputs for the program.,A layer containing the last neurons in the network that produces given outputs for the program.,https://www.techopedia.com/definition/33263/output-layer-neural-networks,,,AIO:Layer
AIO:HiddenLayer,AIO:LayerSubset,,,Hidden Layer,FALSE,0.69,"A hidden layer is located between the input and output of the algorithm, in which the function applies weights to the inputs and directs them through an activation function as the output. In short, the hidden layers perform nonlinear transformations of the inputs entered into the network. Hidden layers vary depending on the function of the neural network, and similarly, the layers may vary depending on their associated weights.","A hidden layer is located between the input and output of the algorithm, in which the function applies weights to the inputs and directs them through an activation function as the output. In short, the hidden layers perform nonlinear transformations of the inputs entered into the network. Hidden layers vary depending on the function of the neural network, and similarly, the layers may vary depending on their associated weights.",A layer located between the input and output that performs nonlinear transformations of the inputs entered into the network.,A layer located between the input and output that performs nonlinear transformations of the inputs entered into the network.,https://deepai.org/machine-Learning-glossary-and-terms/hidden-layer-machine-Learning,,,AIO:Layer
AIO:MemoryCellLayer,AIO:LayerSubset,,,Memory Cell Layer,FALSE,#N/A,,,"A layer of cells, each with an internal state or weights.","A layer of cells, each with an internal state or weights.",https://doi.org/10.1162/neco.1997.9.8.1735,,,AIO:Layer
AIO:WeightedLayer,AIO:LayerSubset,,,Weighted Layer,FALSE,#N/A,,,A layer of values to be applied to other cells or neurons in a network.,A layer of values to be applied to other cells or neurons in a network.,,,,AIO:Layer
AIO:AbstractRNNCell,AIO:LayerSubset,,,AbstractRNNCell,FALSE,0.36,Abstract object representing an RNN cell. This is the base class for implementing RNN cells with custom behavior.,,An abstract layer object representing an RNN cell that is the base class for implementing RNN cells with custom behavior.,A layer representing an RNN cell that is the base class for implementing RNN cells with custom behavior.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/AbstractRNNCell,,,AIO:Layer
AIO:AdditionLayer,AIO:LayerSubset,,,Addition Layer,FALSE,#N/A,,,A layer that adds inputs from one or more other layers to cells or neurons of a target layer.,A layer that adds inputs from one or more other layers to cells or neurons of a target layer.,,,,AIO:Layer
AIO:StackedRNNCellsLayer,AIO:LayerSubset,,,StackedRNNCells Layer,FALSE,0.52,Wrapper allowing a stack of RNN cells to behave as a single cell. Used to implement efficient stacked RNNs.,Wrapper allowing a stack of RNN cells to behave as a single cell. Used to implement efficient stacked RNNs.,A layer that allows a stack of RNN cells to behave as a single cell.,A layer that allows a stack of RNN cells to behave as a single cell.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/StackedRNNCells,,,AIO:Layer
AIO:ActivationLayer,AIO:LayerSubset,,,Activation Layer,FALSE,0.50,Applies an activation function to an output.,Applies an activation function to an output.,A layer that applies an activation function to an output.,A layer that applies an activation function to an output.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Activation,,,AIO:Layer
AIO:RegularizationLayer,AIO:LayerSubset,,,Regularization Layer,FALSE,0.52,Regularizers allow you to apply penalties on layer parameters or layer activity during optimization. These penalties are summed into the loss function that the network optimizes. Regularization penalties are applied on a per-layer basis.,Regularizers allow you to apply penalties on layer parameters or layer activity during optimization. These penalties are summed into the loss function that the network optimizes. Regularization penalties are applied on a per-layer basis.,A layer that applies penalties on layer parameters or layer activity during optimization summed into the loss function that the network optimizes.,A layer that applies penalties on layer parameters or layer activity during optimization summed into the loss function that the network optimizes.,https://keras.io/api/layers/regularizers/,,,AIO:Layer
AIO:WrapperLayer,AIO:LayerSubset,,,Wrapper Layer,FALSE,0.83,"Abstract wrapper base class. Wrappers take another layer and augment it in various ways. Do not use this class as a layer, it is only an abstract base class. Two usable wrappers are the TimeDistributed and Bidirectional wrappers.","Abstract wrapper base class. Wrappers take another layer and augment it in various ways. Do not use this class as a layer, it is only an abstract base class. Two usable wrappers are the TimeDistributed and Bidirectional wrappers.",An abstract base class for wrappers that augment the functionality of another layer.,A layer that augment the functionality of another layer.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Wrapper,,,AIO:Layer
AIO:DotLayer,AIO:LayerSubset,,,Dot Layer,FALSE,0.73,"Layer that computes a dot product between samples in two tensors. E.g. if applied to a list of two tensors a and b of shape (batch_size, n), the output will be a tensor of shape (batch_size, 1) where each entry i will be the dot product between a[i] and b[i].","Layer that computes a dot product between samples in two tensors. E.g. if applied to a list of two tensors a and b of shape (batch_size, n), the output will be a tensor of shape (batch_size, 1) where each entry i will be the dot product between a[i] and b[i].",A layer that computes a dot product between samples in two tensors.,A layer that computes a dot product between samples in two tensors.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dot,,,AIO:Layer
AIO:ConvolutionalLayer,AIO:LayerSubset,,,Convolutional Layer,FALSE,0.61,"A convolutional layer is the main building block of a CNN. It contains a set of filters (or kernels), parameters of which are to be learned throughout the training. The size of the filters is usually smaller than the actual image. Each filter convolves with the image and creates an activation map.","A convolutional layer is the main building block of a CNN. It contains a set of filters (or kernels), parameters of which are to be learned throughout the training. The size of the filters is usually smaller than the actual image. Each filter convolves with the image and creates an activation map.",A layer that contains a set of filters (or kernels) parameters of which are to be learned throughout the training.,A layer that contains a set of filters (or kernels) parameters of which are to be learned throughout the training.,https://www.sciencedirect.com/topics/engineering/convolutional-layer,,,AIO:Layer
AIO:Cropping3DLayer,AIO:LayerSubset,,,Cropping3D Layer,FALSE,0.87,Cropping layer for 3D data (e.g. spatial or spatio-temporal).,Cropping layer for 3D data (e.g. spatial or spatio-temporal).,A layer that crops along spatial dimensions (depth,A layer that crops along spatial dimensions (depth,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Cropping3D,,,AIO:Layer
AIO:Cropping2DLayer,AIO:LayerSubset,,,Cropping2D Layer,FALSE,0.64,"Cropping layer for 2D input (e.g. picture). It crops along spatial dimensions, i.e. height and width.","Cropping layer for 2D input (e.g. picture). It crops along spatial dimensions, i.e. height and width.",A layer that crops along spatial dimensions (i.e. height and width) for 2D input.,A layer that crops along spatial dimensions (i.e. height and width) for 2D input.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Cropping2D,,,AIO:Layer
AIO:LayerLayer,AIO:LayerSubset,,,Layer Layer,FALSE,0.93,"This is the class from which all layers inherit. A layer is a callable object that takes as input one or more tensors and that outputs one or more tensors. It involves computation, defined in the call() method, and a state (weight variables). State can be created in various places, at the convenience of the subclass implementer: in __init__(); in the optional build() method, which is invoked by the first __call__() to the layer, and supplies the shape(s) of the input(s), which may not have been known at initialization time; in the first invocation of call(), with some caveats discussed below. Users will just instantiate a layer and then treat it as a callable.","This is the class from which all layers inherit. A layer is a callable object that takes as input one or more tensors and that outputs one or more tensors. It involves computation, defined in the call() method, and a state (weight variables). State can be created in various places, at the convenience of the subclass implementer: in __init__(); in the optional build() method, which is invoked by the first __call__() to the layer, and supplies the shape(s) of the input(s), which may not have been known at initialization time; in the first invocation of call(), with some caveats discussed below. Users will just instantiate a layer and then treat it as a callable.",The base class from which all layers inherit.,A layer that form which other layers can inherit.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Layer,,,AIO:Layer
AIO:AttentionLayer,AIO:LayerSubset,,,Attention Layer,FALSE,0.79,"Dot-product attention layer, a.k.a. Luong-style attention.","Dot-product attention layer, a.k.a. Luong-style attention.",A layer that implements dot-product attention also known as Luong-style attention.,A layer that implements dot-product attention also known as Luong-style attention.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Attention,,,AIO:Layer
AIO:NoiseDenseLayer,AIO:LayerSubset,,,Noise Dense Layer,FALSE,0.90,"Noisy dense layer that injects random noise to the weights of dense layer. Noisy dense layers are fully connected layers whose weights and biases are augmented by factorised Gaussian noise. The factorised Gaussian noise is controlled through gradient descent by a second weights layer. A NoisyDense layer implements the operation: $$ \mathrm{NoisyDense}(x) = \mathrm{activation}(\mathrm{dot}(x, \mu + (\sigma \cdot \epsilon)) \mathrm{bias}) $$ where mu is the standard weights layer, epsilon is the factorised Gaussian noise, and delta is a second weights layer which controls epsilon.","Noisy dense layer that injects random noise to the weights of dense layer. Noisy dense layers are fully connected layers whose weights and biases are augmented by factorised Gaussian noise. The factorised Gaussian noise is controlled through gradient descent by a second weights layer. A NoisyDense layer implements the operation: $$ \mathrm{NoisyDense}(x) = \mathrm{activation}(\mathrm{dot}(x, \mu + (\sigma \cdot \epsilon)) \mathrm{bias}) $$ where mu is the standard weights layer, epsilon is the factorised Gaussian noise, and delta is a second weights layer which controls epsilon.",A layer that is a densely-connected neural network layer with added noise for regularization.,A layer that is a densely-connected neural network layer with added noise for regularization.,https://www.tensorflow.org/addons/api_docs/python/tfa/layers/NoisyDense,,,AIO:Layer
AIO:DenseLayer,AIO:LayerSubset,,,Dense Layer,FALSE,0.77,Just your regular densely-connected NN layer.,Just your regular densely-connected NN layer.,A layer that is a regular densely-connected neural network layer.,A layer that is a regular densely-connected neural network layer.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dense,,,AIO:Layer
AIO:ReshapingLayer,AIO:LayerSubset,Reshape Layer,,Reshaping Layer,FALSE,0.50,Reshape layers are used to change the shape of the input.,Reshape layers are used to change the shape of the input.,A layer that is used to change the shape of the input.,A layer that is used to change the shape of the input.,https://keras.io/api/layers/reshaping_layers/reshape/,,,AIO:Layer
AIO:MaskingLayer,AIO:LayerSubset,,,Masking Layer,FALSE,0.80,"Masks a sequence by using a mask value to skip timesteps. For each timestep in the input tensor (dimension #1 in the tensor), if all values in the input tensor at that timestep are equal to mask_value, then the timestep will be masked (skipped) in all downstream layers (as long as they support masking). If any downstream layer does not support masking yet receives such an input mask, an exception will be raised.","Masks a sequence by using a mask value to skip timesteps. For each timestep in the input tensor (dimension #1 in the tensor), if all values in the input tensor at that timestep are equal to mask_value, then the timestep will be masked (skipped) in all downstream layers (as long as they support masking). If any downstream layer does not support masking yet receives such an input mask, an exception will be raised.",A layer that masks a sequence by using a mask value to skip timesteps.,A layer that masks a sequence by using a mask value to skip timesteps.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Masking,,,AIO:Layer
AIO:KernelLayer,AIO:LayerSubset,,,Kernel Layer,FALSE,#N/A,,,A layer that obtains the dot product of input values or subsets of input values.,A layer that obtains the dot product of input values or subsets of input values.,,,,AIO:Layer
AIO:CategoricalFeaturesPreprocessingLayer,AIO:LayerSubset,,,Categorical Features Preprocessing Layer,FALSE,0.00,A layer that performs categorical data preprocessing operations.,,A layer that performs categorical data preprocessing operations.,A layer that performs categorical data preprocessing operations.,https://keras.io/guides/preprocessing_layers/,,,AIO:Layer
AIO:PreprocessingLayer,AIO:LayerSubset,,,Preprocessing Layer,FALSE,0.00,A layer that performs data preprocessing operations.,,A layer that performs data preprocessing operations.,A layer that performs data preprocessing operations.,https://www.tensorflow.org/guide/keras/preprocessing_layers,,,AIO:Layer
AIO:ImageAugmentationLayer,AIO:LayerSubset,,,Image Augmentation Layer,FALSE,0.00,A layer that performs image data preprocessing augmentations.,,A layer that performs image data preprocessing augmentations.,A layer that performs image data preprocessing augmentations.,https://keras.io/guides/preprocessing_layers/,,,AIO:Layer
AIO:ImagePreprocessingLayer,AIO:LayerSubset,,,Image Preprocessing Layer,FALSE,0.00,A layer that performs image data preprocessing operations.,,A layer that performs image data preprocessing operations.,A layer that performs image data preprocessing operations.,https://keras.io/guides/preprocessing_layers/,,,AIO:Layer
AIO:NumericalFeaturesPreprocessingLayer,AIO:LayerSubset,,,Numerical Features Preprocessing Layer,FALSE,0.00,A layer that performs numerical data preprocessing operations.,,A layer that performs numerical data preprocessing operations.,A layer that performs numerical data preprocessing operations.,https://keras.io/guides/preprocessing_layers/,,,AIO:Layer
AIO:TextPreprocessingLayer,AIO:LayerSubset,,,Text Preprocessing Layer,FALSE,0.00,A layer that performs text data preprocessing operations.,,A layer that performs text data preprocessing operations.,A layer that performs text data preprocessing operations.,https://keras.io/guides/preprocessing_layers/,,,AIO:Layer
AIO:GRUCellLayer,AIO:LayerSubset,,,GRUCell Layer,FALSE,0.52,"Cell class for the GRU layer. This class processes one step within the whole time sequence input, whereas tf.keras.layer.GRU processes the whole sequence.","Cell class for the GRU layer. This class processes one step within the whole time sequence input, whereas tf.keras.layer.GRU processes the whole sequence.",A layer that processes one step within the whole time sequence input for a GRU layer.,A layer that processes one step within the whole time sequence input for a GRU layer.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/GRUCell,,,AIO:Layer
AIO:SimpleRNNCellLayer,AIO:LayerSubset,,,SimpleRNNCell Layer,FALSE,0.63,"Cell class for SimpleRNN. This class processes one step within the whole time sequence input, whereas tf.keras.layer.SimpleRNN processes the whole sequence.","Cell class for SimpleRNN. This class processes one step within the whole time sequence input, whereas tf.keras.layer.SimpleRNN processes the whole sequence.",A layer that processes one step within the whole time sequence input for a SimpleRNN layer.,A layer that processes one step within the whole time sequence input for a SimpleRNN layer.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/SimpleRNNCell,,,AIO:Layer
AIO:LSTMCellLayer,AIO:LayerSubset,,,LSTMCell Layer,FALSE,0.78,Cell class for the LSTM layer.,Cell class for the LSTM layer.,A layer that processes one step within the whole time sequence input for an LSTM layer.,A layer that processes one step within the whole time sequence input for an LSTM layer.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/LSTMCell,,,AIO:Layer
AIO:DenseFeaturesLayer,AIO:LayerSubset,,,DenseFeatures Layer,FALSE,0.86,"A layer that produces a dense Tensor based on given feature_columns. Generally a single example in training data is described with FeatureColumns. At the first layer of the model, this column oriented data should be converted to a single Tensor. This layer can be called multiple times with different features. This is the V2 version of this layer that uses name_scopes to create variables instead of variable_scopes. But this approach currently lacks support for partitioned variables. In that case, use the V1 version instead.","A layer that produces a dense Tensor based on given feature_columns. Generally a single example in training data is described with FeatureColumns. At the first layer of the model, this column oriented data should be converted to a single Tensor. This layer can be called multiple times with different features. This is the V2 version of this layer that uses name_scopes to create variables instead of variable_scopes. But this approach currently lacks support for partitioned variables. In that case, use the V1 version instead.",A layer that produces a dense tensor based on given feature columns.,A layer that produces a dense tensor based on given feature columns.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/DenseFeatures,,,AIO:Layer
AIO:PoolingLayer,AIO:LayerSubset,,,Pooling Layer,FALSE,0.55,Pooling layers serve the dual purposes of mitigating the sensitivity of convolutional layers to location and of spatially downsampling representations.,Pooling layers serve the dual purposes of mitigating the sensitivity of convolutional layers to location and of spatially downsampling representations.,A layer that serves to mitigate the sensitivity of convolutional layers to location and spatially downsample representations.,A layer that serves to mitigate the sensitivity of convolutional layers to location and spatially downsample representations.,https://d2l.ai/chapter_convolutional-neural-networks/pooling.html,,,AIO:Layer
AIO:InputSpecLayer,AIO:LayerSubset,,,InputSpec Layer,FALSE,0.94,"Specifies the rank, dtype and shape of every input to a layer. Layers can expose (if appropriate) an input_spec attribute: an instance of InputSpec, or a nested structure of InputSpec instances (one per input tensor). These objects enable the layer to run input compatibility checks for input structure, input rank, input shape, and input dtype. A None entry in a shape is compatible with any dimension, a None shape is compatible with any shape.","Specifies the rank, dtype and shape of every input to a layer. Layers can expose (if appropriate) an input_spec attribute: an instance of InputSpec, or a nested structure of InputSpec instances (one per input tensor). These objects enable the layer to run input compatibility checks for input structure, input rank, input shape, and input dtype. A None entry in a shape is compatible with any dimension, a None shape is compatible with any shape.",A layer that specifies the rank,A layer that specifies the rank,https://www.tensorflow.org/api_docs/python/tf/keras/layers/InputSpec,,,AIO:Layer
AIO:EmbeddingLayer,AIO:LayerSubset,,,Embedding Layer,FALSE,0.36,Turns positive integers (indexes) into dense vectors of fixed size.,,A layer that turns positive integers (indexes) into dense vectors of fixed size.,A layer that turns positive integers (indexes) into dense vectors of fixed size.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Embedding,,,AIO:Layer
AIO:UpSampling3DLayer,AIO:LayerSubset,,,UpSampling3D Layer,FALSE,0.93,Upsampling layer for 3D inputs.,Upsampling layer for 3D inputs.,A layer that upsamples the input by repeating each depth,A layer that upsamples the input by repeating each depth,https://www.tensorflow.org/api_docs/python/tf/keras/layers/UpSampling3D,,,AIO:Layer
AIO:UpSampling2DLayer,AIO:LayerSubset,,,UpSampling2D Layer,FALSE,0.85,Upsampling layer for 2D inputs. Repeats the rows and columns of the data by size[0] and size[1] respectively.,Upsampling layer for 2D inputs. Repeats the rows and columns of the data by size[0] and size[1] respectively.,A layer that upsamples the input by repeating each row and column size times.,A layer that upsamples the input by repeating each row and column size times.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/UpSampling2D,,,AIO:Layer
AIO:LocallyconnectedLayer,AIO:LayerSubset,,,Locally-connected Layer,FALSE,#N/A,,,"A layer that works similarly to the Convolution1D layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input.","A layer that works similarly to the Convolution1D layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input.",https://faroit.com/keras-docs/1.2.2/layers/local/,,,AIO:Layer
AIO:LambdaLayer,AIO:LayerSubset,,,Lambda Layer,FALSE,0.45,Wraps arbitrary expressions as a Layer object.,Wraps arbitrary expressions as a Layer object.,A layer that wraps arbitrary expressions as a Layer object.,A layer that wraps arbitrary expressions as a Layer object.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Lambda,,,AIO:Layer
AIO:PolicyLayer,AIO:LayerSubset,,,Policy Layer,FALSE,#N/A,,,"A layer that, after taking a set of states or values as input, predicts a probability distribution of actions to take.","A layer that, after taking a set of states or values as input, predicts a probability distribution of actions to take.",,,,AIO:Layer
AIO:InputLayerLayer,AIO:LayerSubset,,,InputLayer Layer,FALSE,0.18,Layer to be used as an entry point into a Network (a graph of layers).,,A layer to be used as an entry point into a Network (a graph of layers).,A layer to be used as an entry point into a Network (a graph of layers).,https://www.tensorflow.org/api_docs/python/tf/keras/layers/InputLayer,,,AIO:Layer
AIO:MergingLayer,AIO:LayerSubset,,,Merging Layer,FALSE,0.00,A layer used to merge a list of inputs.,,A layer used to merge a list of inputs.,A layer used to merge a list of inputs.,https://www.tutorialspoint.com/keras/keras_merge_layer.htm,,,AIO:Layer
AIO:LocallyConnected1DLayer,AIO:LayerSubset,,,LocallyConnected1D Layer,FALSE,0.71,"Locally-connected layer for 1D inputs. The LocallyConnected1D layer works similarly to the Conv1D layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input.","Locally-connected layer for 1D inputs. The LocallyConnected1D layer works similarly to the Conv1D layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input.",A locally-connected layer for 1D inputs where each patch of the input is convolved with a different set of filters.,A locally-connected layer for 1D inputs where each patch of the input is convolved with a different set of filters.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/LocallyConnected1D,,,AIO:LocallyconnectedLayer
AIO:LocallyConnected2DLayer,AIO:LayerSubset,,,LocallyConnected2D Layer,FALSE,0.71,"Locally-connected layer for 2D inputs. The LocallyConnected2D layer works similarly to the Conv2D layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input.","Locally-connected layer for 2D inputs. The LocallyConnected2D layer works similarly to the Conv2D layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input.",A locally-connected layer for 2D inputs where each patch of the input is convolved with a different set of filters.,A locally-connected layer for 2D inputs where each patch of the input is convolved with a different set of filters.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/LocallyConnected2D,,,AIO:LocallyconnectedLayer
AIO:AddLayer,AIO:LayerSubset,,,Add Layer,FALSE,0.66,"Layer that adds a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape).","Layer that adds a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape).",A merging layer that adds a list of inputs taking as input a list of tensors all of the same shape.,A merging layer that adds a list of inputs taking as input a list of tensors all of the same shape.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Add,,,AIO:MergingLayer
AIO:AverageLayer,AIO:LayerSubset,,,Average Layer,FALSE,0.63,"Layer that averages a list of inputs element-wise. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape).","Layer that averages a list of inputs element-wise. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape).",A merging layer that averages a list of inputs element-wise taking as input a list of tensors all of the same shape.,A merging layer that averages a list of inputs element-wise taking as input a list of tensors all of the same shape.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Average,,,AIO:MergingLayer
AIO:MaximumLayer,AIO:LayerSubset,,,Maximum Layer,FALSE,0.67,"Layer that computes the maximum (element-wise) a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape).","Layer that computes the maximum (element-wise) a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape).",A merging layer that computes the maximum (element-wise) of a list of inputs.,A merging layer that computes the maximum (element-wise) of a list of inputs.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Maximum,,,AIO:MergingLayer
AIO:MinimumLayer,AIO:LayerSubset,,,Minimum Layer,FALSE,0.67,"Layer that computes the minimum (element-wise) a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape).","Layer that computes the minimum (element-wise) a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape).",A merging layer that computes the minimum (element-wise) of a list of inputs.,A merging layer that computes the minimum (element-wise) of a list of inputs.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Minimum,,,AIO:MergingLayer
AIO:ConcatenateLayer,AIO:LayerSubset,,,Concatenate Layer,FALSE,0.56,"Layer that concatenates a list of inputs. It takes as input a list of tensors, all of the same shape except for the concatenation axis, and returns a single tensor that is the concatenation of all inputs.","Layer that concatenates a list of inputs. It takes as input a list of tensors, all of the same shape except for the concatenation axis, and returns a single tensor that is the concatenation of all inputs.",A merging layer that concatenates a list of inputs taking as input a list of tensors all of the same shape except for the concatenation axis.,A merging layer that concatenates a list of inputs taking as input a list of tensors all of the same shape except for the concatenation axis.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Concatenate,,,AIO:MergingLayer
AIO:MultiplyLayer,AIO:LayerSubset,,,Multiply Layer,FALSE,0.73,"Layer that multiplies (element-wise) a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape).","Layer that multiplies (element-wise) a list of inputs. It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape).",A merging layer that multiplies (element-wise) a list of inputs.,A merging layer that multiplies (element-wise) a list of inputs.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Multiply,,,AIO:MergingLayer
AIO:SubtractLayer,AIO:LayerSubset,,,Subtract Layer,FALSE,0.87,"Layer that subtracts two inputs. It takes as input a list of tensors of size 2, both of the same shape, and returns a single tensor, (inputs[0] - inputs[1]), also of the same shape.","Layer that subtracts two inputs. It takes as input a list of tensors of size 2, both of the same shape, and returns a single tensor, (inputs[0] - inputs[1]), also of the same shape.",A merging layer that subtracts two inputs.,A merging layer that subtracts two inputs.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Subtract,,,AIO:MergingLayer
AIO:GroupNormLayer,AIO:LayerSubset,GroupNorm|GroupNorm,,GroupNorm Layer,FALSE,0.68,Applies Group Normalization over a mini-batch of inputs as described in the paper Group Normalization,Applies Group Normalization over a mini-batch of inputs as described in the paper Group Normalization,A normalization layer that applies Group Normalization over a mini-batch of inputs.,A normalization layer that applies Group Normalization over a mini-batch of inputs.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:NormalizationLayer
AIO:InstanceNorm1DLayer,AIO:LayerSubset,InstanceNorm1D|InstanceNorm1D|InstanceNorm1D,,InstanceNorm1D Layer,FALSE,0.69,Applies Instance Normalization over a 2D (unbatched) or 3D (batched) input as described in the paper Instance Normalization: The Missing Ingredient for Fast Stylization.,Applies Instance Normalization over a 2D (unbatched) or 3D (batched) input as described in the paper Instance Normalization: The Missing Ingredient for Fast Stylization.,A normalization layer that applies Instance Normalization over a 2D (unbatched) or 3D (batched) input.,A normalization layer that applies Instance Normalization over a 2D (unbatched) or 3D (batched) input.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:NormalizationLayer
AIO:InstanceNorm2D,AIO:LayerSubset,,,InstanceNorm2D,FALSE,0.59,Applies Instance Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension) as described in the paper Instance Normalization: The Missing Ingredient for Fast Stylization.,Applies Instance Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension) as described in the paper Instance Normalization: The Missing Ingredient for Fast Stylization.,A normalization layer that applies Instance Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension).,A normalization layer that applies Instance Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension).,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:NormalizationLayer
AIO:InstanceNorm3DLayer,AIO:LayerSubset,InstanceNorm3D,,InstanceNorm3D Layer,FALSE,0.59,Applies Instance Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension) as described in the paper Instance Normalization: The Missing Ingredient for Fast Stylization.,Applies Instance Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension) as described in the paper Instance Normalization: The Missing Ingredient for Fast Stylization.,A normalization layer that applies Instance Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension).,A normalization layer that applies Instance Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension).,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:NormalizationLayer
AIO:LayerNormLayer,AIO:LayerSubset,LayerNorm,,LayerNorm Layer,FALSE,0.68,Applies Layer Normalization over a mini-batch of inputs as described in the paper Layer Normalization,Applies Layer Normalization over a mini-batch of inputs as described in the paper Layer Normalization,A normalization layer that applies Layer Normalization over a mini-batch of inputs.,A normalization layer that applies Layer Normalization over a mini-batch of inputs.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:NormalizationLayer
AIO:LayerNormalizationLayer,AIO:LayerSubset,,,LayerNormalization Layer,FALSE,0.89,"Layer normalization layer (Ba et al., 2016). Normalize the activations of the previous layer for each given example in a batch independently, rather than across a batch like Batch Normalization. i.e. applies a transformation that maintains the mean activation within each example close to 0 and the activation standard deviation close to 1. Given a tensor inputs, moments are calculated and normalization is performed across the axes specified in axis.","Layer normalization layer (Ba et al., 2016). Normalize the activations of the previous layer for each given example in a batch independently, rather than across a batch like Batch Normalization. i.e. applies a transformation that maintains the mean activation within each example close to 0 and the activation standard deviation close to 1. Given a tensor inputs, moments are calculated and normalization is performed across the axes specified in axis.",A normalization layer that applies Layer Normalization over the inputs.,A normalization layer that applies Layer Normalization over the inputs.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/LayerNormalization,,,AIO:NormalizationLayer
AIO:LocalResponseNormLayer,AIO:LayerSubset,LocalResponseNorm,,LocalResponseNorm Layer,FALSE,0.57,"Applies local response normalization over an input signal composed of several input planes, where channels occupy the second dimension.","Applies local response normalization over an input signal composed of several input planes, where channels occupy the second dimension.",A normalization layer that applies local response normalization over an input signal composed of several input planes.,A normalization layer that applies local response normalization over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:NormalizationLayer
AIO:BatchNormalizationLayer,AIO:LayerSubset,BatchNorm,,BatchNormalization Layer,FALSE,0.87,"Layer that normalizes its inputs. Batch normalization applies a transformation that maintains the mean output close to 0 and the output standard deviation close to 1. Importantly, batch normalization works differently during training and during inference. During training (i.e. when using fit() or when calling the layer/model with the argument training=True), the layer normalizes its output using the mean and standard deviation of the current batch of inputs. That is to say, for each channel being normalized, the layer returns gamma * (batch - mean(batch)) / sqrt(var(batch) + epsilon) + beta, where: epsilon is small constant (configurable as part of the constructor arguments), gamma is a learned scaling factor (initialized as 1), which can be disabled by passing scale=False to the constructor. beta is a learned offset factor (initialized as 0), which can be disabled by passing center=False to the constructor. During inference (i.e. when using evaluate() or predict() or when calling the layer/model with the argument training=False (which is the default), the layer normalizes its output using a moving average of the mean and standard deviation of the batches it has seen during training. That is to say, it returns gamma * (batch - self.moving_mean) / sqrt(self.moving_var + epsilon) + beta. self.moving_mean and self.moving_var are non-trainable variables that are updated each time the layer in called in training mode, as such: moving_mean = moving_mean * momentum + mean(batch) * (1 - momentum) moving_var = moving_var * momentum + var(batch) * (1 - momentum).","Layer that normalizes its inputs. Batch normalization applies a transformation that maintains the mean output close to 0 and the output standard deviation close to 1. Importantly, batch normalization works differently during training and during inference. During training (i.e. when using fit() or when calling the layer/model with the argument training=True), the layer normalizes its output using the mean and standard deviation of the current batch of inputs. That is to say, for each channel being normalized, the layer returns gamma * (batch - mean(batch)) / sqrt(var(batch) + epsilon) + beta, where: epsilon is small constant (configurable as part of the constructor arguments), gamma is a learned scaling factor (initialized as 1), which can be disabled by passing scale=False to the constructor. beta is a learned offset factor (initialized as 0), which can be disabled by passing center=False to the constructor. During inference (i.e. when using evaluate() or predict() or when calling the layer/model with the argument training=False (which is the default), the layer normalizes its output using a moving average of the mean and standard deviation of the batches it has seen during training. That is to say, it returns gamma * (batch - self.moving_mean) / sqrt(self.moving_var + epsilon) + beta. self.moving_mean and self.moving_var are non-trainable variables that are updated each time the layer in called in training mode, as such: moving_mean = moving_mean * momentum + mean(batch) * (1 - momentum) moving_var = moving_var * momentum + var(batch) * (1 - momentum).",A normalization layer that normalizes its inputs applying a transformation that maintains the mean close to 0 and the standard deviation close to 1.,A normalization layer that normalizes its inputs applying a transformation that maintains the mean close to 0 and the standard deviation close to 1.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/BatchNormalization,,,AIO:NormalizationLayer
AIO:NormalizationLayer,AIO:LayerSubset,,,Normalization Layer,FALSE,0.25,A preprocessing layer which normalizes continuous features.,,A preprocessing layer that normalizes continuous features.,A numerical features prepreprocessing layer that normalizes continuous features.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Normalization,,,AIO:NumericalFeaturesPreprocessingLayer
AIO:DiscretizationLayer,AIO:LayerSubset,,,Discretization Layer,FALSE,0.00,A preprocessing layer which buckets continuous features by ranges.,,A preprocessing layer which buckets continuous features by ranges.,A numerical features prepreprocessing layer which buckets continuous features by ranges.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Discretization,,,AIO:NumericalFeaturesPreprocessingLayer
AIO:LPPool1DLayer,AIO:LayerSubset,LPPool1D,,LPPool1D Layer,FALSE,0.35,Applies a 1D power-average pooling over an input signal composed of several input planes.,,A pooling layer that applies 1D power-average pooling over an input signal composed of several input planes.,A pooling layer that applies 1D power-average pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:LPPool2DLayer,AIO:LayerSubset,LPPool2D,,LPPool2D Layer,FALSE,0.35,Applies a 2D power-average pooling over an input signal composed of several input planes.,,A pooling layer that applies 2D power-average pooling over an input signal composed of several input planes.,A pooling layer that applies 2D power-average pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:AdaptiveAvgPool1DLayer,AIO:LayerSubset,AdaptiveAvgPool1D,,AdaptiveAvgPool1D Layer,FALSE,0.28,Applies a 1D adaptive average pooling over an input signal composed of several input planes.,,A pooling layer that applies a 1D adaptive average pooling over an input signal composed of several input planes.,A pooling layer that applies a 1D adaptive average pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:AdaptiveMaxPool1DLayer,AIO:LayerSubset,AdaptiveMaxPool1D,,AdaptiveMaxPool1D Layer,FALSE,0.28,Applies a 1D adaptive max pooling over an input signal composed of several input planes.,,A pooling layer that applies a 1D adaptive max pooling over an input signal composed of several input planes.,A pooling layer that applies a 1D adaptive max pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:AvgPool1DLayer,AIO:LayerSubset,AvgPool1D,,AvgPool1D Layer,FALSE,0.29,Applies a 1D average pooling over an input signal composed of several input planes.,,A pooling layer that applies a 1D average pooling over an input signal composed of several input planes.,A pooling layer that applies a 1D average pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:AdaptiveAvgPool2DLayer,AIO:LayerSubset,AdaptiveAvgPool2D,,AdaptiveAvgPool2D Layer,FALSE,0.28,Applies a 2D adaptive average pooling over an input signal composed of several input planes.,,A pooling layer that applies a 2D adaptive average pooling over an input signal composed of several input planes.,A pooling layer that applies a 2D adaptive average pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:AdaptiveMaxPool2DLayer,AIO:LayerSubset,AdaptiveMaxPool2D,,AdaptiveMaxPool2D Layer,FALSE,0.28,Applies a 2D adaptive max pooling over an input signal composed of several input planes.,,A pooling layer that applies a 2D adaptive max pooling over an input signal composed of several input planes.,A pooling layer that applies a 2D adaptive max pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:AvgPool2DLayer,AIO:LayerSubset,AvgPool2D,,AvgPool2D Layer,FALSE,0.29,Applies a 2D average pooling over an input signal composed of several input planes.,,A pooling layer that applies a 2D average pooling over an input signal composed of several input planes.,A pooling layer that applies a 2D average pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:FractionalMaxPool2DLayer,AIO:LayerSubset,FractionalMaxPool2D,,FractionalMaxPool2D Layer,FALSE,0.28,Applies a 2D fractional max pooling over an input signal composed of several input planes.,,A pooling layer that applies a 2D fractional max pooling over an input signal composed of several input planes.,A pooling layer that applies a 2D fractional max pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:AdaptiveAvgPool3DLayer,AIO:LayerSubset,AdaptiveAvgPool3D,,AdaptiveAvgPool3D Layer,FALSE,0.28,Applies a 3D adaptive average pooling over an input signal composed of several input planes.,,A pooling layer that applies a 3D adaptive average pooling over an input signal composed of several input planes.,A pooling layer that applies a 3D adaptive average pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:AdaptiveMaxPool3DLayer,AIO:LayerSubset,AdaptiveMaxPool3D,,AdaptiveMaxPool3D Layer,FALSE,0.28,Applies a 3D adaptive max pooling over an input signal composed of several input planes.,,A pooling layer that applies a 3D adaptive max pooling over an input signal composed of several input planes.,A pooling layer that applies a 3D adaptive max pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:AvgPool3DLayer,AIO:LayerSubset,AvgPool3D,,AvgPool3D Layer,FALSE,0.29,Applies a 3D average pooling over an input signal composed of several input planes.,,A pooling layer that applies a 3D average pooling over an input signal composed of several input planes.,A pooling layer that applies a 3D average pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:FractionalMaxPool3DLayer,AIO:LayerSubset,FractionalMaxPool3D,,FractionalMaxPool3D Layer,FALSE,0.28,Applies a 3D fractional max pooling over an input signal composed of several input planes.,,A pooling layer that applies a 3D fractional max pooling over an input signal composed of several input planes.,A pooling layer that applies a 3D fractional max pooling over an input signal composed of several input planes.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:MaxUnpool1DLayer,AIO:LayerSubset,MaxUnpool1D,,MaxUnpool1D Layer,FALSE,0.55,Computes a partial inverse of MaxPool1D.,Computes a partial inverse of MaxPool1D.,A pooling layer that computes a partial inverse of MaxPool1D.,A pooling layer that computes a partial inverse of MaxPool1D.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:MaxUnpool2DLayer,AIO:LayerSubset,MaxUnpool2D,,MaxUnpool2D Layer,FALSE,0.55,Computes a partial inverse of MaxPool2D.,Computes a partial inverse of MaxPool2D.,A pooling layer that computes a partial inverse of MaxPool2D.,A pooling layer that computes a partial inverse of MaxPool2D.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:MaxUnpool3DLayer,AIO:LayerSubset,MaxUnpool3D,,MaxUnpool3D Layer,FALSE,0.55,Computes a partial inverse of MaxPool3D.,Computes a partial inverse of MaxPool3D.,A pooling layer that computes a partial inverse of MaxPool3D.,A pooling layer that computes a partial inverse of MaxPool3D.,https://pytorch.org/docs/stable/nn.html#pooling-layers,,,AIO:PoolingLayer
AIO:AveragePooling3DLayer,AIO:LayerSubset,AvgPool3D,,AveragePooling3D Layer,FALSE,0.82,"Average pooling operation for 3D data (spatial or spatio-temporal). Downsamples the input along its spatial dimensions (depth, height, and width) by taking the average value over an input window (of size defined by pool_size) for each channel of the input. The window is shifted by strides along each dimension.","Average pooling operation for 3D data (spatial or spatio-temporal). Downsamples the input along its spatial dimensions (depth, height, and width) by taking the average value over an input window (of size defined by pool_size) for each channel of the input. The window is shifted by strides along each dimension.",A pooling layer that performs average pooling for 3D data (spatial or spatio-temporal).,A pooling layer that performs average pooling for 3D data (spatial or spatio-temporal).,https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling3D,,,AIO:PoolingLayer
AIO:AveragePooling2DLayer,AIO:LayerSubset,AvgPool2D,,AveragePooling2D Layer,FALSE,0.93,"Average pooling operation for spatial data. Downsamples the input along its spatial dimensions (height and width) by taking the average value over an input window (of size defined by pool_size) for each channel of the input. The window is shifted by strides along each dimension. The resulting output when using ""valid"" padding option has a shape (number of rows or columns) of: output_shape = math.floor((input_shape - pool_size) / strides) + 1 (when input_shape >= pool_size). The resulting output shape when using the ""same"" padding option is: output_shape = math.floor((input_shape - 1) / strides) + 1.","Average pooling operation for spatial data. Downsamples the input along its spatial dimensions (height and width) by taking the average value over an input window (of size defined by pool_size) for each channel of the input. The window is shifted by strides along each dimension. The resulting output when using ""valid"" padding option has a shape (number of rows or columns) of: output_shape = math.floor((input_shape - pool_size) / strides) + 1 (when input_shape >= pool_size). The resulting output shape when using the ""same"" padding option is: output_shape = math.floor((input_shape - 1) / strides) + 1.",A pooling layer that performs average pooling for spatial data.,A pooling layer that performs average pooling for spatial data.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling2D,,,AIO:PoolingLayer
AIO:AveragePooling1DLayer,AIO:LayerSubset,AvgPool1D,,AveragePooling1D Layer,FALSE,0.90,"Average pooling for temporal data. Downsamples the input representation by taking the average value over the window defined by pool_size. The window is shifted by strides. The resulting output when using ""valid"" padding option has a shape of: output_shape = (input_shape - pool_size + 1) / strides). The resulting output shape when using the ""same"" padding option is: output_shape = input_shape / strides.","Average pooling for temporal data. Downsamples the input representation by taking the average value over the window defined by pool_size. The window is shifted by strides. The resulting output when using ""valid"" padding option has a shape of: output_shape = (input_shape - pool_size + 1) / strides). The resulting output shape when using the ""same"" padding option is: output_shape = input_shape / strides.",A pooling layer that performs average pooling for temporal data.,A pooling layer that performs average pooling for temporal data.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/AveragePooling1D,,,AIO:PoolingLayer
AIO:GlobalAveragePooling3DLayer,AIO:LayerSubset,GlobalAvgPool3D,,GlobalAveragePooling3D Layer,FALSE,0.62,Global Average pooling operation for 3D data.,Global Average pooling operation for 3D data.,A pooling layer that performs global average pooling operation for 3D data.,A pooling layer that performs global average pooling operation for 3D data.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling3D,,,AIO:PoolingLayer
AIO:GlobalAveragePooling2DLayer,AIO:LayerSubset,GlobalAvgPool2D,,GlobalAveragePooling2D Layer,FALSE,0.50,Global average pooling operation for spatial data.,Global average pooling operation for spatial data.,A pooling layer that performs global average pooling operation for spatial data.,A pooling layer that performs global average pooling operation for spatial data.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling2D,,,AIO:PoolingLayer
AIO:GlobalAveragePooling1DLayer,AIO:LayerSubset,GlobalAvgPool1D,,GlobalAveragePooling1D Layer,FALSE,0.50,Global average pooling operation for temporal data.,Global average pooling operation for temporal data.,A pooling layer that performs global average pooling operation for temporal data.,A pooling layer that performs global average pooling operation for temporal data.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalAveragePooling1D,,,AIO:PoolingLayer
AIO:GlobalMaxPooling3DLayer,AIO:LayerSubset,GlobalMaxPool3D,,GlobalMaxPooling3D Layer,FALSE,0.62,Global Max pooling operation for 3D data.,Global Max pooling operation for 3D data.,A pooling layer that performs global max pooling operation for 3D data.,A pooling layer that performs global max pooling operation for 3D data.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPool3D,,,AIO:PoolingLayer
AIO:GlobalMaxPooling2DLayer,AIO:LayerSubset,GlobalMaxPool2D,,GlobalMaxPooling2D Layer,FALSE,0.50,Global max pooling operation for spatial data.,Global max pooling operation for spatial data.,A pooling layer that performs global max pooling operation for spatial data.,A pooling layer that performs global max pooling operation for spatial data.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPool2D,,,AIO:PoolingLayer
AIO:GlobalMaxPooling1DLayer,AIO:LayerSubset,GlobalMaxPool1D,,GlobalMaxPooling1D Layer,FALSE,0.54,Global max pooling operation for 1D temporal data.,Global max pooling operation for 1D temporal data.,A pooling layer that performs global max pooling operation for temporal data.,A pooling layer that performs global max pooling operation for temporal data.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPool1D,,,AIO:PoolingLayer
AIO:MaxPooling3DLayer,AIO:LayerSubset,MaxPool3D|MaxPooling3D,,MaxPooling3D Layer,FALSE,0.82,"Max pooling operation for 3D data (spatial or spatio-temporal). Downsamples the input along its spatial dimensions (depth, height, and width) by taking the maximum value over an input window (of size defined by pool_size) for each channel of the input. The window is shifted by strides along each dimension.","Max pooling operation for 3D data (spatial or spatio-temporal). Downsamples the input along its spatial dimensions (depth, height, and width) by taking the maximum value over an input window (of size defined by pool_size) for each channel of the input. The window is shifted by strides along each dimension.",A pooling layer that performs max pooling operation for 3D data (spatial or spatio-temporal).,A pooling layer that performs max pooling operation for 3D data (spatial or spatio-temporal).,https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool3D,,,AIO:PoolingLayer
AIO:MaxPooling2DLayer,AIO:LayerSubset,MaxPool2D|MaxPooling2D,,MaxPooling2D Layer,FALSE,0.58,Max pooling operation for 2D spatial data.,Max pooling operation for 2D spatial data.,A pooling layer that performs max pooling operation for spatial data.,A pooling layer that performs max pooling operation for spatial data.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool2D,,,AIO:PoolingLayer
AIO:MaxPooling1DLayer,AIO:LayerSubset,MaxPool1D|MaxPooling1D,,MaxPooling1D Layer,FALSE,0.91,"Max pooling operation for 1D temporal data. Downsamples the input representation by taking the maximum value over a spatial window of size pool_size. The window is shifted by strides. The resulting output, when using the ""valid"" padding option, has a shape of: output_shape = (input_shape - pool_size + 1) / strides) The resulting output shape when using the ""same"" padding option is: output_shape = input_shape / strides.","Max pooling operation for 1D temporal data. Downsamples the input representation by taking the maximum value over a spatial window of size pool_size. The window is shifted by strides. The resulting output, when using the ""valid"" padding option, has a shape of: output_shape = (input_shape - pool_size + 1) / strides) The resulting output shape when using the ""same"" padding option is: output_shape = input_shape / strides.",A pooling layer that performs max pooling operation for temporal data.,A pooling layer that performs max pooling operation for temporal data.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/MaxPool1D,,,AIO:PoolingLayer
AIO:TimeDistributedLayer,AIO:LayerSubset,,,TimeDistributed Layer,FALSE,0.85,"This wrapper allows to apply a layer to every temporal slice of an input. Every input should be at least 3D, and the dimension of index one of the first input will be considered to be the temporal dimension. Consider a batch of 32 video samples, where each sample is a 128x128 RGB image with channels_last data format, across 10 timesteps. The batch input shape is (32, 10, 128, 128, 3). You can then use TimeDistributed to apply the same Conv2D layer to each of the 10 timesteps, independently:","This wrapper allows to apply a layer to every temporal slice of an input. Every input should be at least 3D, and the dimension of index one of the first input will be considered to be the temporal dimension. Consider a batch of 32 video samples, where each sample is a 128x128 RGB image with channels_last data format, across 10 timesteps. The batch input shape is (32, 10, 128, 128, 3). You can then use TimeDistributed to apply the same Conv2D layer to each of the 10 timesteps, independently:",A wrapper layer that applies a layer to every temporal slice of an input.,A recurrent layer that applies a layer to every temporal slice of an input.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/TimeDistributed,,,AIO:RecurrentLayer
AIO:SimpleRNNLayer,AIO:LayerSubset,,,SimpleRNN Layer,FALSE,0.44,Fully-connected RNN where the output is to be fed back to input.,Fully-connected RNN where the output is to be fed back to input.,A recurrent layer that implements a fully-connected RNN where the output is to be fed back to input.,A recurrent layer that implements a fully-connected RNN where the output is to be fed back to input.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/SimpleRNN,,,AIO:RecurrentLayer
AIO:GRULayer,AIO:LayerSubset,,,GRU Layer,FALSE,0.96,"Gated Recurrent Unit - Cho et al. 2014. Based on available runtime hardware and constraints, this layer will choose different implementations (cuDNN-based or pure-TensorFlow) to maximize the performance. If a GPU is available and all the arguments to the layer meet the requirement of the cuDNN kernel (see below for details), the layer will use a fast cuDNN implementation. The requirements to use the cuDNN implementation are: activation == tanh, recurrent_activation == sigmoid, recurrent_dropout == 0, unroll is False, use_bias is True, reset_after is True. Inputs, if use masking, are strictly right-padded. Eager execution is enabled in the outermost context. There are two variants of the GRU implementation. The default one is based on v3 and has reset gate applied to hidden state before matrix multiplication. The other one is based on original and has the order reversed. The second variant is compatible with CuDNNGRU (GPU-only) and allows inference on CPU. Thus it has separate biases for kernel and recurrent_kernel. To use this variant, set reset_after=True and recurrent_activation='sigmoid'.","Gated Recurrent Unit - Cho et al. 2014. Based on available runtime hardware and constraints, this layer will choose different implementations (cuDNN-based or pure-TensorFlow) to maximize the performance. If a GPU is available and all the arguments to the layer meet the requirement of the cuDNN kernel (see below for details), the layer will use a fast cuDNN implementation. The requirements to use the cuDNN implementation are: activation == tanh, recurrent_activation == sigmoid, recurrent_dropout == 0, unroll is False, use_bias is True, reset_after is True. Inputs, if use masking, are strictly right-padded. Eager execution is enabled in the outermost context. There are two variants of the GRU implementation. The default one is based on v3 and has reset gate applied to hidden state before matrix multiplication. The other one is based on original and has the order reversed. The second variant is compatible with CuDNNGRU (GPU-only) and allows inference on CPU. Thus it has separate biases for kernel and recurrent_kernel. To use this variant, set reset_after=True and recurrent_activation='sigmoid'.",A recurrent layer that implements the Gated Recurrent Unit architecture.,A recurrent layer that implements the Gated Recurrent Unit architecture.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/GRU,,,AIO:RecurrentLayer
AIO:LSTMLayer,AIO:LayerSubset,,,LSTM Layer,FALSE,0.94,"Long Short-Term Memory layer - Hochreiter 1997. Based on available runtime hardware and constraints, this layer will choose different implementations (cuDNN-based or pure-TensorFlow) to maximize the performance. If a GPU is available and all the arguments to the layer meet the requirement of the cuDNN kernel (see below for details), the layer will use a fast cuDNN implementation. The requirements to use the cuDNN implementation are: 1. activation == tanh, 2. recurrent_activation == sigmoid, 3. recurrent_dropout == 0, 4. unroll is False, 5. use_bias is True, 6. Inputs, if use masking, are strictly right-padded, 7. Eager execution is enabled in the outermost context.","Long Short-Term Memory layer - Hochreiter 1997. Based on available runtime hardware and constraints, this layer will choose different implementations (cuDNN-based or pure-TensorFlow) to maximize the performance. If a GPU is available and all the arguments to the layer meet the requirement of the cuDNN kernel (see below for details), the layer will use a fast cuDNN implementation. The requirements to use the cuDNN implementation are: 1. activation == tanh, 2. recurrent_activation == sigmoid, 3. recurrent_dropout == 0, 4. unroll is False, 5. use_bias is True, 6. Inputs, if use masking, are strictly right-padded, 7. Eager execution is enabled in the outermost context.",A recurrent layer that implements the Long Short-Term Memory architecture.,A recurrent layer that implements the Long Short-Term Memory architecture.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/LSTM,,,AIO:RecurrentLayer
AIO:BidirectionalLayer,AIO:LayerSubset,,,Bidirectional Layer,FALSE,0.73,Bidirectional wrapper for RNNs.,Bidirectional wrapper for RNNs.,A recurrent layer that is a bidirectional wrapper for RNNs.,A recurrent layer that is a bidirectional wrapper for RNNs.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Bidirectional,,,AIO:RecurrentLayer
AIO:UnitNormalizationLayer,AIO:LayerSubset,,,UnitNormalization Layer,FALSE,0.43,Unit normalization layer. Normalize a batch of inputs so that each input in the batch has a L2 norm equal to 1 (across the axes specified in axis).,Unit normalization layer. Normalize a batch of inputs so that each input in the batch has a L2 norm equal to 1 (across the axes specified in axis).,A normalization layer that normalizes a batch of inputs so that each input in the batch has a L2 norm equal to 1.,A recurrent layer that normalizes a batch of inputs so that each input in the batch has a L2 norm equal to 1.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/UnitNormalization,,,AIO:RecurrentLayer
AIO:GaussianNoiseLayer,AIO:LayerSubset,,,GaussianNoise Layer,FALSE,0.89,"Apply additive zero-centered Gaussian noise. This is useful to mitigate overfitting (you could see it as a form of random data augmentation). Gaussian Noise (GS) is a natural choice as corruption process for real valued inputs. As it is a regularization layer, it is only active at training time.","Apply additive zero-centered Gaussian noise. This is useful to mitigate overfitting (you could see it as a form of random data augmentation). Gaussian Noise (GS) is a natural choice as corruption process for real valued inputs. As it is a regularization layer, it is only active at training time.",A regularization layer that applies additive zero-centered Gaussian noise.,A regularization layer that applies additive zero-centered Gaussian noise.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/GaussianNoise,,,AIO:RegularizationLayer
AIO:AlphaDropoutLayer,AIO:LayerSubset,,,AlphaDropout Layer,FALSE,0.74,"Applies Alpha Dropout to the input. Alpha Dropout is a Dropout that keeps mean and variance of inputs to their original values, in order to ensure the self-normalizing property even after this dropout. Alpha Dropout fits well to Scaled Exponential Linear Units by randomly setting activations to the negative saturation value.","Applies Alpha Dropout to the input. Alpha Dropout is a Dropout that keeps mean and variance of inputs to their original values, in order to ensure the self-normalizing property even after this dropout. Alpha Dropout fits well to Scaled Exponential Linear Units by randomly setting activations to the negative saturation value.",A regularization layer that applies Alpha Dropout to the input keeping mean and variance of inputs to ensure self-normalizing property.,A regularization layer that applies Alpha Dropout to the input keeping mean and variance of inputs to ensure self-normalizing property.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/AlphaDropout,,,AIO:RegularizationLayer
AIO:ActivityRegularizationLayer,AIO:LayerSubset,,,ActivityRegularization Layer,FALSE,0.31,Layer that applies an update to the cost function based input activity.,,A regularization layer that applies an update to the cost function based on input activity.,A regularization layer that applies an update to the cost function based on input activity.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/ActivityRegularization,,,AIO:RegularizationLayer
AIO:DropoutLayer,AIO:LayerSubset,,,Dropout Layer,FALSE,0.92,"Applies Dropout to the input. The Dropout layer randomly sets input units to 0 with a frequency of rate at each step during training time, which helps prevent overfitting. Inputs not set to 0 are scaled up by 1/(1 - rate) such that the sum over all inputs is unchanged. Note that the Dropout layer only applies when training is set to True such that no values are dropped during inference. When using model.fit, training will be appropriately set to True automatically, and in other contexts, you can set the kwarg explicitly to True when calling the layer. (This is in contrast to setting trainable=False for a Dropout layer. trainable does not affect the layer's behavior, as Dropout does not have any variables/weights that can be frozen during training.)","Applies Dropout to the input. The Dropout layer randomly sets input units to 0 with a frequency of rate at each step during training time, which helps prevent overfitting. Inputs not set to 0 are scaled up by 1/(1 - rate) such that the sum over all inputs is unchanged. Note that the Dropout layer only applies when training is set to True such that no values are dropped during inference. When using model.fit, training will be appropriately set to True automatically, and in other contexts, you can set the kwarg explicitly to True when calling the layer. (This is in contrast to setting trainable=False for a Dropout layer. trainable does not affect the layer's behavior, as Dropout does not have any variables/weights that can be frozen during training.)",A regularization layer that applies Dropout to the input,A regularization layer that applies Dropout to the input,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dropout,,,AIO:RegularizationLayer
AIO:GaussianDropoutLayer,AIO:LayerSubset,,,GaussianDropout Layer,FALSE,0.75,"Apply multiplicative 1-centered Gaussian noise. As it is a regularization layer, it is only active at training time.","Apply multiplicative 1-centered Gaussian noise. As it is a regularization layer, it is only active at training time.",A regularization layer that applies multiplicative 1-centered Gaussian noise.,A regularization layer that applies multiplicative 1-centered Gaussian noise.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/GaussianDropout,,,AIO:RegularizationLayer
AIO:SpatialDropout1DLayer,AIO:LayerSubset,,,SpatialDropout1D Layer,FALSE,0.80,"Spatial 1D version of Dropout. This version performs the same function as Dropout, however, it drops entire 1D feature maps instead of individual elements. If adjacent frames within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective Learning rate decrease. In this case, SpatialDropout1D will help promote independence between feature maps and should be used instead.","Spatial 1D version of Dropout. This version performs the same function as Dropout, however, it drops entire 1D feature maps instead of individual elements. If adjacent frames within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective Learning rate decrease. In this case, SpatialDropout1D will help promote independence between feature maps and should be used instead.",A regularization layer that performs the same function as Dropout but drops entire 1D feature maps instead of individual elements.,A regularization layer that performs the same function as Dropout but drops entire 1D feature maps instead of individual elements.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/SpatialDropout1D,,,AIO:RegularizationLayer
AIO:SpatialDropout2DLayer,AIO:LayerSubset,,,SpatialDropout2D Layer,FALSE,0.80,"Spatial 2D version of Dropout. This version performs the same function as Dropout, however, it drops entire 2D feature maps instead of individual elements. If adjacent pixels within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective Learning rate decrease. In this case, SpatialDropout2D will help promote independence between feature maps and should be used instead.a","Spatial 2D version of Dropout. This version performs the same function as Dropout, however, it drops entire 2D feature maps instead of individual elements. If adjacent pixels within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective Learning rate decrease. In this case, SpatialDropout2D will help promote independence between feature maps and should be used instead.a",A regularization layer that performs the same function as Dropout but drops entire 2D feature maps instead of individual elements.,A regularization layer that performs the same function as Dropout but drops entire 2D feature maps instead of individual elements.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/SpatialDropout2D,,,AIO:RegularizationLayer
AIO:SpatialDropout3DLayer,AIO:LayerSubset,,,SpatialDropout3D Layer,FALSE,0.80,"Spatial 3D version of Dropout. This version performs the same function as Dropout, however, it drops entire 3D feature maps instead of individual elements. If adjacent voxels within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective Learning rate decrease. In this case, SpatialDropout3D will help promote independence between feature maps and should be used instead.","Spatial 3D version of Dropout. This version performs the same function as Dropout, however, it drops entire 3D feature maps instead of individual elements. If adjacent voxels within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective Learning rate decrease. In this case, SpatialDropout3D will help promote independence between feature maps and should be used instead.",A regularization layer that performs the same function as Dropout but drops entire 3D feature maps instead of individual elements.,A regularization layer that performs the same function as Dropout but drops entire 3D feature maps instead of individual elements.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/SpatialDropout3D,,,AIO:RegularizationLayer
AIO:Cropping1DLayer,AIO:LayerSubset,,,Cropping1D Layer,FALSE,0.55,Cropping layer for 1D input (e.g. temporal sequence). It crops along the time dimension (axis 1).,Cropping layer for 1D input (e.g. temporal sequence). It crops along the time dimension (axis 1).,A layer that crops along the time dimension (axis 1) for 1D input.,A reshaping layer that crops along the time dimension (axis 1) for 1D input.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Cropping1D,,,AIO:ReshapingLayer
AIO:FlattenLayer,AIO:LayerSubset,,,Flatten Layer,FALSE,0.92,Flattens the input. Does not affect the batch size.,Flattens the input. Does not affect the batch size.,A layer that flattens the input,A reshaping layer that flattens the input,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Flatten,,,AIO:ReshapingLayer
AIO:PermuteLayer,AIO:LayerSubset,,,Permute Layer,FALSE,0.55,Permutes the dimensions of the input according to a given pattern. Useful e.g. connecting RNNs and convnets.,Permutes the dimensions of the input according to a given pattern. Useful e.g. connecting RNNs and convnets.,A layer that permutes the dimensions of the input according to a given pattern.,A reshaping layer that permutes the dimensions of the input according to a given pattern.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Permute,,,AIO:ReshapingLayer
AIO:RepeatVectorLayer,AIO:LayerSubset,,,RepeatVector Layer,FALSE,0.56,Repeats the input n times.,Repeats the input n times.,A layer that repeats the input n times.,A reshaping layer that repeats the input n times.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/RepeatVector,,,AIO:ReshapingLayer
AIO:ReshapeLayer,AIO:LayerSubset,,,Reshape Layer,FALSE,0.30,Layer that reshapes inputs into the given shape.,,A layer that reshapes the inputs into the given shape.,A reshaping layer that reshapes the inputs into the given shape.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Reshape,,,AIO:ReshapingLayer
AIO:UpSampling1DLayer,AIO:LayerSubset,,,UpSampling1D Layer,FALSE,0.52,Upsampling layer for 1D inputs. Repeats each temporal step size times along the time axis.,Upsampling layer for 1D inputs. Repeats each temporal step size times along the time axis.,A layer that upsamples the input by repeating each temporal step size times along the time axis.,A reshaping layer that upsamples the input by repeating each temporal step size times along the time axis.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/UpSampling1D,,,AIO:ReshapingLayer
AIO:ZeroPadding3DLayer,AIO:LayerSubset,,,ZeroPadding3D Layer,FALSE,0.93,Zero-padding layer for 3D data (spatial or spatio-temporal).,Zero-padding layer for 3D data (spatial or spatio-temporal).,A layer that zero-pads the input along the depth,A reshaping layer that zero-pads the input along the depth,https://www.tensorflow.org/api_docs/python/tf/keras/layers/ZeroPadding3D,,,AIO:ReshapingLayer
AIO:ZeroPadding2DLayer,AIO:LayerSubset,,,ZeroPadding2D Layer,FALSE,0.88,"Zero-padding layer for 2D input (e.g. picture). This layer can add rows and columns of zeros at the top, bottom, left and right side of an image tensor.","Zero-padding layer for 2D input (e.g. picture). This layer can add rows and columns of zeros at the top, bottom, left and right side of an image tensor.",A layer that zero-pads the input along the height and width dimensions.,A reshaping layer that zero-pads the input along the height and width dimensions.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/ZeroPadding2D,,,AIO:ReshapingLayer
AIO:ZeroPadding1DLayer,AIO:LayerSubset,,,ZeroPadding1D Layer,FALSE,0.87,Zero-padding layer for 1D input (e.g. temporal sequence).,Zero-padding layer for 1D input (e.g. temporal sequence).,A layer that zero-pads the input along the time axis.,A reshaping layer that zero-pads the input along the time axis.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/ZeroPadding1D,,,AIO:ReshapingLayer
AIO:TextVectorizationLayer,AIO:LayerSubset,,,TextVectorization Layer,FALSE,0.18,A preprocessing layer which maps text features to integer sequences.,,A preprocessing layer that maps text features to integer sequences.,A text preprocessing layer that maps text features to integer sequences.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/TextVectorization,,,AIO:TextPreprocessingLayer
AIO:PReLULayer,AIO:LayerSubset,,,PReLU Layer,FALSE,1.00,Parametric Rectified Linear Unit.,Parametric Rectified Linear Unit.,An activation layer that applies parametric rectified linear unit function element-wise.,An activation layer that applies parametric rectified linear unit function element-wise.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/PReLU,,,AIO:ActivationLayer
AIO:ELULayer,AIO:LayerSubset,,,ELU Layer,FALSE,0.85,Exponential Linear Unit.,Exponential Linear Unit.,An activation layer that applies the Exponential Linear Unit (ELU) function element-wise.,An activation layer that applies the Exponential Linear Unit (ELU) function element-wise.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/ELU,,,AIO:ActivationLayer
AIO:LeakyReLULayer,AIO:LayerSubset,,,LeakyReLU Layer,FALSE,1.00,Leaky version of a Rectified Linear Unit.,Leaky version of a Rectified Linear Unit.,An activation layer that applies the leaky rectified linear unit function element-wise.,An activation layer that applies the leaky rectified linear unit function element-wise.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/LeakyReLU,,,AIO:ActivationLayer
AIO:ReLULayer,AIO:LayerSubset,,,ReLU Layer,FALSE,0.96,"Rectified Linear Unit activation function. With default values, it returns element-wise max(x, 0).","Rectified Linear Unit activation function. With default values, it returns element-wise max(x, 0).",An activation layer that applies the rectified linear unit function element-wise.,An activation layer that applies the rectified linear unit function element-wise.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/ReLU,,,AIO:ActivationLayer
AIO:SoftmaxLayer,AIO:LayerSubset,,,Softmax Layer,FALSE,0.92,Softmax activation function.,Softmax activation function.,An activation layer that applies the softmax function to the inputs.,An activation layer that applies the softmax function to the inputs.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Softmax,,,AIO:ActivationLayer
AIO:ThresholdedReLULayer,AIO:LayerSubset,,,ThresholdedReLU Layer,FALSE,1.00,Thresholded Rectified Linear Unit.,Thresholded Rectified Linear Unit.,An activation layer that applies the thresholded rectified linear unit function element-wise.,An activation layer that applies the thresholded rectified linear unit function element-wise.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/ThresholdedReLU,,,AIO:ActivationLayer
AIO:MultiHeadAttentionLayer,AIO:LayerSubset,,,MultiHeadAttention Layer,FALSE,0.96,"MultiHeadAttention layer. This is an implementation of multi-headed attention as described in the paper ""Attention is all you Need"" (Vaswani et al., 2017). If query, key, value are the same, then this is self-attention. Each timestep in query attends to the corresponding sequence in key, and returns a fixed-width vector.This layer first projects query, key and value. These are (effectively) a list of tensors of length num_attention_heads, where the corresponding shapes are (batch_size, <query dimensions>, key_dim), (batch_size, <key/value dimensions>, key_dim), (batch_size, <key/value dimensions>, value_dim).Then, the query and key tensors are dot-producted and scaled. These are softmaxed to obtain attention probabilities. The value tensors are then interpolated by these probabilities, then concatenated back to a single tensor. Finally, the result tensor with the last dimension as value_dim can take an linear projection and return. When using MultiHeadAttention inside a custom Layer, the custom Layer must implement build() and call MultiHeadAttention's _build_from_signature(). This enables weights to be restored correctly when the model is loaded.","MultiHeadAttention layer. This is an implementation of multi-headed attention as described in the paper ""Attention is all you Need"" (Vaswani et al., 2017). If query, key, value are the same, then this is self-attention. Each timestep in query attends to the corresponding sequence in key, and returns a fixed-width vector.This layer first projects query, key and value. These are (effectively) a list of tensors of length num_attention_heads, where the corresponding shapes are (batch_size, <query dimensions>, key_dim), (batch_size, <key/value dimensions>, key_dim), (batch_size, <key/value dimensions>, value_dim).Then, the query and key tensors are dot-producted and scaled. These are softmaxed to obtain attention probabilities. The value tensors are then interpolated by these probabilities, then concatenated back to a single tensor. Finally, the result tensor with the last dimension as value_dim can take an linear projection and return. When using MultiHeadAttention inside a custom Layer, the custom Layer must implement build() and call MultiHeadAttention's _build_from_signature(). This enables weights to be restored correctly when the model is loaded.",An attention layer that allows the model to attend to information from different representation subspaces.,An attention layer that allows the model to attend to information from different representation subspaces.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/MultiHeadAttention,,,AIO:AttentionLayer
AIO:AdditiveAttentionLayer,AIO:LayerSubset,,,AdditiveAttention Layer,FALSE,0.79,"Additive attention layer, a.k.a. Bahdanau-style attention.","Additive attention layer, a.k.a. Bahdanau-style attention.",An attention layer that implements additive attention also known as Bahdanau-style attention.,An attention layer that implements additive attention also known as Bahdanau-style attention.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/AdditiveAttention,,,AIO:AttentionLayer
AIO:CenterCropLayer,AIO:LayerSubset,,,CenterCrop Layer,FALSE,0.77,"A preprocessing layer which crops images. This layers crops the central portion of the images to a target size. If an image is smaller than the target size, it will be resized and cropped so as to return the largest possible window in the image that matches the target aspect ratio. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats.","A preprocessing layer which crops images. This layers crops the central portion of the images to a target size. If an image is smaller than the target size, it will be resized and cropped so as to return the largest possible window in the image that matches the target aspect ratio. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats.",An image preprocessing layer that crops the central portion of images to a target size.,An image preprocessing layer that crops the central portion of images to a target size.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/CenterCrop,,,AIO:ImagePreprocessingLayer
AIO:RandomBrightnessLayer,AIO:LayerSubset,,,RandomBrightness Layer,FALSE,0.81,"A preprocessing layer which randomly adjusts brightness during training. This layer will randomly increase/reduce the brightness for the input RGB images. At inference time, the output will be identical to the input. Call the layer with training=True to adjust the brightness of the input. Note that different brightness adjustment factors will be apply to each the images in the batch.","A preprocessing layer which randomly adjusts brightness during training. This layer will randomly increase/reduce the brightness for the input RGB images. At inference time, the output will be identical to the input. Call the layer with training=True to adjust the brightness of the input. Note that different brightness adjustment factors will be apply to each the images in the batch.",An image preprocessing layer that randomly adjusts brightness during training.,An image preprocessing layer that randomly adjusts brightness during training.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomBrightness,,,AIO:ImagePreprocessingLayer
AIO:RandomContrastLayer,AIO:LayerSubset,,,RandomContrast Layer,FALSE,0.90,"A preprocessing layer which randomly adjusts contrast during training. This layer will randomly adjust the contrast of an image or images by a random factor. Contrast is adjusted independently for each channel of each image during training. For each channel, this layer computes the mean of the image pixels in the channel and then adjusts each component x of each pixel to (x - mean) * contrast_factor + mean. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and in integer or floating point dtype. By default, the layer will output floats. The output value will be clipped to the range [0, 255], the valid range of RGB colors.","A preprocessing layer which randomly adjusts contrast during training. This layer will randomly adjust the contrast of an image or images by a random factor. Contrast is adjusted independently for each channel of each image during training. For each channel, this layer computes the mean of the image pixels in the channel and then adjusts each component x of each pixel to (x - mean) * contrast_factor + mean. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and in integer or floating point dtype. By default, the layer will output floats. The output value will be clipped to the range [0, 255], the valid range of RGB colors.",An image preprocessing layer that randomly adjusts contrast during training.,An image preprocessing layer that randomly adjusts contrast during training.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomContrast,,,AIO:ImagePreprocessingLayer
AIO:RandomCropLayer,AIO:LayerSubset,,,RandomCrop Layer,FALSE,0.90,"A preprocessing layer which randomly crops images during training. During training, this layer will randomly choose a location to crop images down to a target size. The layer will crop all the images in the same batch to the same cropping location. At inference time, and during training if an input image is smaller than the target size, the input will be resized and cropped so as to return the largest possible window in the image that matches the target aspect ratio. If you need to apply random cropping at inference time, set training to True when calling the layer. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats.","A preprocessing layer which randomly crops images during training. During training, this layer will randomly choose a location to crop images down to a target size. The layer will crop all the images in the same batch to the same cropping location. At inference time, and during training if an input image is smaller than the target size, the input will be resized and cropped so as to return the largest possible window in the image that matches the target aspect ratio. If you need to apply random cropping at inference time, set training to True when calling the layer. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats.",An image preprocessing layer that randomly crops images during training.,An image preprocessing layer that randomly crops images during training.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomCrop,,,AIO:ImagePreprocessingLayer
AIO:RandomFlipLayer,AIO:LayerSubset,,,RandomFlip Layer,FALSE,0.87,"A preprocessing layer which randomly flips images during training. This layer will flip the images horizontally and or vertically based on the mode attribute. During inference time, the output will be identical to input. Call the layer with training=True to flip the input. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats.","A preprocessing layer which randomly flips images during training. This layer will flip the images horizontally and or vertically based on the mode attribute. During inference time, the output will be identical to input. Call the layer with training=True to flip the input. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats.",An image preprocessing layer that randomly flips images during training.,An image preprocessing layer that randomly flips images during training.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomFlip,,,AIO:ImagePreprocessingLayer
AIO:RandomRotationLayer,AIO:LayerSubset,,,RandomRotation Layer,FALSE,0.42,A preprocessing layer which randomly rotates images during training.,A preprocessing layer which randomly rotates images during training.,An image preprocessing layer that randomly rotates images during training.,An image preprocessing layer that randomly rotates images during training.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomRotation,,,AIO:ImagePreprocessingLayer
AIO:RandomTranslationLayer,AIO:LayerSubset,,,RandomTranslation Layer,FALSE,0.84,"A preprocessing layer which randomly translates images during training. This layer will apply random translations to each image during training, filling empty space according to fill_mode. aInput pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats.","A preprocessing layer which randomly translates images during training. This layer will apply random translations to each image during training, filling empty space according to fill_mode. aInput pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats.",An image preprocessing layer that randomly translates images during training.,An image preprocessing layer that randomly translates images during training.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomTranslation,,,AIO:ImagePreprocessingLayer
AIO:RandomHeightLayer,AIO:LayerSubset,,,RandomHeight Layer,FALSE,0.87,"A preprocessing layer which randomly varies image height during training. This layer adjusts the height of a batch of images by a random factor. The input should be a 3D (unbatched) or 4D (batched) tensor in the ""channels_last"" image data format. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. By default, this layer is inactive during inference.","A preprocessing layer which randomly varies image height during training. This layer adjusts the height of a batch of images by a random factor. The input should be a 3D (unbatched) or 4D (batched) tensor in the ""channels_last"" image data format. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. By default, this layer is inactive during inference.",An image preprocessing layer that randomly varies image height during training.,An image preprocessing layer that randomly varies image height during training.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomHeight,,,AIO:ImagePreprocessingLayer
AIO:RandomWidthLayer,AIO:LayerSubset,,,RandomWidth Layer,FALSE,0.87,"A preprocessing layer which randomly varies image width during training. This layer will randomly adjusts the width of a batch of images of a batch of images by a random factor. The input should be a 3D (unbatched) or 4D (batched) tensor in the ""channels_last"" image data format. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. By default, this layer is inactive during inference.","A preprocessing layer which randomly varies image width during training. This layer will randomly adjusts the width of a batch of images of a batch of images by a random factor. The input should be a 3D (unbatched) or 4D (batched) tensor in the ""channels_last"" image data format. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. By default, this layer is inactive during inference.",An image preprocessing layer that randomly varies image width during training.,An image preprocessing layer that randomly varies image width during training.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomWidth,,,AIO:ImagePreprocessingLayer
AIO:RandomZoomLayer,AIO:LayerSubset,,,RandomZoom Layer,FALSE,0.76,"A preprocessing layer which randomly zooms images during training. This layer will randomly zoom in or out on each axis of an image independently, filling empty space according to fill_mode.Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats.","A preprocessing layer which randomly zooms images during training. This layer will randomly zoom in or out on each axis of an image independently, filling empty space according to fill_mode.Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats.",An image preprocessing layer that randomly zooms in or out on images during training.,An image preprocessing layer that randomly zooms in or out on images during training.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomZoom,,,AIO:ImagePreprocessingLayer
AIO:RescalingLayer,AIO:LayerSubset,,,Rescaling Layer,FALSE,0.17,A preprocessing layer which rescales input values to a new range.,,A preprocessing layer that rescales input values to a new range.,An image preprocessing layer that rescales input values to a new range.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Rescaling,,,AIO:ImagePreprocessingLayer
AIO:ResizingLayer,AIO:LayerSubset,,,Resizing Layer,FALSE,0.86,"A preprocessing layer which resizes images. This layer resizes an image input to a target height and width. The input should be a 4D (batched) or 3D (unbatched) tensor in ""channels_last"" format. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. This layer can be called on tf.RaggedTensor batches of input images of distinct sizes, and will resize the outputs to dense tensors of uniform size.","A preprocessing layer which resizes images. This layer resizes an image input to a target height and width. The input should be a 4D (batched) or 3D (unbatched) tensor in ""channels_last"" format. Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats. This layer can be called on tf.RaggedTensor batches of input images of distinct sizes, and will resize the outputs to dense tensors of uniform size.",A preprocessing layer that resizes images to a target size.,An image preprocessing layer that resizes images to a target size.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/Resizing,,,AIO:ImagePreprocessingLayer
AIO:NoisyInputLayer,AIO:LayerSubset,,,Noisy Input Layer,FALSE,#N/A,,,An input layer that adds noise to each value.,An input layer that adds noise to each value.,https://doi.org/10.1109/21.155944,,,AIO:InputLayer
AIO:BackfedInputLayer,AIO:LayerSubset,,,Backfed Input Layer,FALSE,#N/A,,,An input layer that receives values from another layer.,An input layer that receives values from another layer.,,,,AIO:InputLayer
AIO:MatchedInputOutputLayer,AIO:LayerSubset,,,Matched Input-Output Layer,FALSE,#N/A,,,An input layer with a shape corresponding to that of the output layer.,An input layer with a shape corresponding to that of the output layer.,,,,AIO:InputLayer
AIO:RNNLayer,AIO:LayerSubset,,,RNN Layer,FALSE,0.43,Base class for recurrent layers.,Base class for recurrent layers.,The base class for recurrent layers.,The base class for recurrent layers.,https://www.tensorflow.org/api_docs/python/tf/keras/layers/RNN,,,AIO:RecurrentLayer
AIO:LazyInstanceNorm1DLayer,AIO:LayerSubset|AIO:InstanceNormalizationLayerSubset,LazyInstanceNorm1D|LazyInstanceNorm1D|LazyInstanceNorm1D,,LazyInstanceNorm1D Layer,FALSE,0.81,A torch.nn.InstanceNorm1D module with lazy initialization of the num_features argument of the InstanceNorm1D that is inferred from the input.size(1).,A torch.nn.InstanceNorm1D module with lazy initialization of the num_features argument of the InstanceNorm1D that is inferred from the input.size(1).,An instance normalization layer that lazily initializes the num_features argument from the input size for 1D data.,A normalization layer that lazily initializes the num_features argument from the input size for 1D data.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:NormalizationLayer
AIO:LazyInstanceNorm2DLayer,AIO:LayerSubset|AIO:InstanceNormalizationLayerSubset,LazyInstanceNorm2D|LazyInstanceNorm2D|LazyInstanceNorm2D,,LazyInstanceNorm2D Layer,FALSE,0.81,A torch.nn.InstanceNorm2D module with lazy initialization of the num_features argument of the InstanceNorm2D that is inferred from the input.size(1).,A torch.nn.InstanceNorm2D module with lazy initialization of the num_features argument of the InstanceNorm2D that is inferred from the input.size(1).,An instance normalization layer that lazily initializes the num_features argument from the input size for 2D data.,A normalization layer that lazily initializes the num_features argument from the input size for 2D data.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:NormalizationLayer
AIO:LazyInstanceNorm3DLayer,AIO:LayerSubset|AIO:InstanceNormalizationLayerSubset,LazyInstanceNorm3D|LazyInstanceNorm3D|LazyInstanceNorm3D,,LazyInstanceNorm3D Layer,FALSE,0.81,A torch.nn.InstanceNorm3D module with lazy initialization of the num_features argument of the InstanceNorm3D that is inferred from the input.size(1).,A torch.nn.InstanceNorm3D module with lazy initialization of the num_features argument of the InstanceNorm3D that is inferred from the input.size(1).,An instance normalization layer that lazily initializes the num_features argument from the input size for 3D data.,A normalization that lazily initializes the num_features argument from the input size for 3D data.,https://pytorch.org/docs/stable/nn.html#normalization-layers,,,AIO:NormalizationLayer
AIO:SupervisedBiclustering,AIO:MachineLearningSubset,Supervised Block Clustering|Supervised Co-clustering|Supervised Two-mode Clustering|Supervised Two-way Clustering|Supervised Joint Clustering,,Supervised Biclustering,FALSE,0.36,"Methods that simultaneously cluster the rows and columns of a labeled matrix, considering data labels to enhance cluster coherence.",,A biclustering task focused on methods that simultaneously cluster the rows and columns of a labeled matrix considering data labels to enhance cluster coherence.,A biclustering task focused on methods that simultaneously cluster the rows and columns of a labeled matrix considering data labels to enhance cluster coherence.,https://en.wikipedia.org/wiki/Biclustering,,,AIO:Biclustering
AIO:UnsupervisedBiclustering,AIO:MachineLearningSubset,Unsupervised Block Clustering|Unsupervised Co-clustering|Unsupervised Two-mode Clustering|Unsupervised Two-way Clustering|Unsupervised Joint Clustering,,Unsupervised Biclustering,FALSE,0.28,Methods that simultaneously cluster the rows and columns of an unlabeled input matrix to identify submatrices with coherent patterns.,,A biclustering task focused on methods that simultaneously cluster the rows and columns of an unlabeled input matrix to identify submatrices with coherent patterns.,A biclustering task focused on methods that simultaneously cluster the rows and columns of an unlabeled input matrix to identify submatrices with coherent patterns.,https://en.wikipedia.org/wiki/Biclustering,,,AIO:Biclustering
AIO:KnearestNeighborClassificationAlgorithm,AIO:MachineLearningSubset,KNN Classification|K-NN Classification,,K-nearest Neighbor Classification Algorithm,FALSE,#N/A,,,"A classification and clustering that classifies objects by a plurality vote of its neighbors, assigning each object to the class most common among its k nearest neighbors.","A classification and clustering that classifies objects by a plurality vote of its neighbors, assigning each object to the class most common among its k nearest neighbors.",https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm,,,AIO:Clustering
AIO:BinaryClassification,AIO:MachineLearningSubset,,,Binary Classification,FALSE,0.39,Methods that classify elements into two groups based on a classification rule.,,A machine learning task focused on methods that classify elements into two groups based on a classification rule.,A classification focused on methods that classify elements into two groups based on a classification rule.,https://en.wikipedia.org/wiki/Binary_classification,,,AIO:Classification
AIO:MulticlassClassification,AIO:MachineLearningSubset,Multinomial Classification,,Multiclass Classification,FALSE,0.44,Methods that classify instances into one of three or more classes.,Methods that classify instances into one of three or more classes.,A machine learning task focused on methods that classify instances into one of three or more classes.,A classification focused on methods that classify instances into one of three or more classes.,https://en.wikipedia.org/wiki/Multiclass_classification,,,AIO:Classification
AIO:HierarchicalClassification,AIO:MachineLearningSubset,,,Hierarchical Classification,FALSE,0.50,Methods that group things according to a hierarchy.,Methods that group things according to a hierarchy.,A classification task focused on methods that group things according to a hierarchy.,A classification focused on methods that group things according to a hierarchy.,https://en.wikipedia.org/wiki/Hierarchical_classification,,,AIO:Classification
AIO:DecisionTree,AIO:MachineLearningSubset,,,Decision Tree,FALSE,0.41,"A decision support tool that uses a tree-like model of decisions and their possible consequences, including chance event outcomes, resource costs, and utilities.","A decision support tool that uses a tree-like model of decisions and their possible consequences, including chance event outcomes, resource costs, and utilities.",A machine learning model that uses a tree-like model of decisions and their possible consequences including chance event outcomes resource costs and utilities.,A classification that uses a tree-like model of decisions and their possible consequences including chance event outcomes resource costs and utilities.,https://en.wikipedia.org/wiki/Decision_tree,,,AIO:Classification
AIO:UnsupervisedClustering,AIO:MachineLearningSubset,Unsupervised Cluster Analysis,,Unsupervised Clustering,FALSE,0.26,Methods that group a set of unlabeled objects such that objects in the same group are more similar to each other than to those in other groups.,,A clustering task focused on methods that group a set of unlabeled objects such that objects in the same group are more similar to each other than to those in other groups.,A clustering focused on methods that group a set of unlabeled objects such that objects in the same group are more similar to each other than to those in other groups.,https://en.wikipedia.org/wiki/Cluster_analysis,,,AIO:Clustering
AIO:SupervisedClustering,AIO:MachineLearningSubset,Supervised Cluster Analysis,,Supervised Clustering,FALSE,0.38,"Methods that group labeled objects such that objects in the same group have similar labels, relative to those in other groups.",,A clustering task focused on methods that group labeled objects such that objects in the same group have similar labels relative to those in other groups.,A clustering focused on methods that group labeled objects such that objects in the same group have similar labels relative to those in other groups.,https://en.wikipedia.org/wiki/Cluster_analysis,,,AIO:Clustering
AIO:HierarchicalClustering,AIO:MachineLearningSubset,HCL,,Hierarchical Clustering,FALSE,0.55,Methods that build a hierarchy of clusters.,Methods that build a hierarchy of clusters.,A clustering method that builds a hierarchy of clusters.,A clustering that builds a hierarchy of clusters.,https://en.wikipedia.org/wiki/Hierarchical_clustering,,,AIO:Clustering
AIO:tDistributedStochasticNeighborembedding,AIO:MachineLearningSubset,tSNE|t-SNE,,t-Distributed Stochastic Neighbor embedding,FALSE,#N/A,,,A dimensionality reduction for visualizing high-dimensional data by giving each datapoint a location in a two or three-dimensional map.,A dimensionality reduction for visualizing high-dimensional data by giving each datapoint a location in a two or three-dimensional map.,https://en.wikipedia.org/wiki/T-distributed_stochastic_neighbor_embedding,,,AIO:DimensionalityReduction
AIO:ManifoldLearning,AIO:MachineLearningSubset,,,Manifold Learning,FALSE,0.25,Methods based on the assumption that observed data lie on a low-dimensional manifold embedded in a higher-dimensional space.,,A dimensionality reduction method based on the assumption that observed data lie on a low-dimensional manifold embedded in a higher-dimensional space.,A dimensionality reduction method based on the assumption that observed data lie on a low-dimensional manifold embedded in a higher-dimensional space.,https://arxiv.org/abs/2011.01307,,,AIO:DimensionalityReduction
AIO:PrincipalComponentAnalysis,AIO:MachineLearningSubset,PCA,,Principal Component Analysis,FALSE,0.32,"A method for analyzing large datasets with high-dimensional features per observation, increasing data interpretability while preserving maximum information and enabling visualization of multidimensional data.",,A dimensionality reduction method for analyzing large datasets with high-dimensional features per observation increasing data interpretability while preserving maximum information and enabling visualization.,A dimensionality reduction method for analyzing large datasets with high-dimensional features per observation increasing data interpretability while preserving maximum information and enabling visualization.,https://en.wikipedia.org/wiki/Principal_component_analysis,,,AIO:DimensionalityReduction
AIO:MultidimensionalScaling,AIO:MachineLearningSubset,MDS,,Multidimensional Scaling,FALSE,0.08,A method that translates information about the pairwise distances among a set of objects or individuals into a configuration of points mapped into an abstract Cartesian space.,,A dimensionality reduction method that translates information about the pairwise distances among a set of objects or individuals into a configuration of points mapped into an abstract Cartesian space.,A dimensionality reduction method that translates information about the pairwise distances among a set of objects or individuals into a configuration of points mapped into an abstract Cartesian space.,https://en.wikipedia.org/wiki/Multidimensional_scaling,,,AIO:DimensionalityReduction
AIO:MachineLearningTask,AIO:MachineLearningSubset,,Machine Learning,Machine Learning Task,FALSE,#N/A,A field of inquiry devoted to understanding and building methods that learn from data to improve performance on a set of tasks.,,#N/A,A process intended to build methods that learn from data.,https://doi.org/10.6028/NIST.SP.1270,,,owl:Thing
AIO:UnsupervisedLearning,AIO:MachineLearningSubset,,,Unsupervised Learning,FALSE,0.60,Algorithms that learn patterns from unlabeled data.,Algorithms that learn patterns from unlabeled data.,A type of machine learning focused on algorithms that learn patterns from unlabeled data.,A machine learning task focused on algorithms that learn patterns from unlabeled data.,https://en.wikipedia.org/wiki/Unsupervised_learning,,,AIO:MachineLearningTask
AIO:SurvivalAnalysis,AIO:MachineLearningSubset,,,Survival Analysis,FALSE,0.32,"Methods for analyzing the expected duration of time until one or more events occur, such as death in biological organisms or failure in mechanical systems.",,A machine learning task focused on methods for analyzing the expected duration of time until one or more events occur such as death in biological organisms or failure in mechanical systems.,A machine learning task focused on methods for analyzing the expected duration of time until one or more events occur such as death in biological organisms or failure in mechanical systems.,https://en.wikipedia.org/wiki/Survival_analysis,,,AIO:MachineLearningTask
AIO:TimeSeriesAnalysis,AIO:MachineLearningSubset,,,Time Series Analysis,FALSE,0.42,Methods for analyzing time series data to extract meaningful statistics and characteristics.,Methods for analyzing time series data to extract meaningful statistics and characteristics.,A machine learning task focused on methods for analyzing time series data to extract meaningful statistics and characteristics.,A machine learning task focused on methods for analyzing time series data to extract meaningful statistics and characteristics.,https://en.wikipedia.org/wiki/Time_series,,,AIO:MachineLearningTask
AIO:ReinforcementLearning,AIO:MachineLearningSubset,,,Reinforcement Learning,FALSE,0.27,"Methods that do not require labeled input/output pairs or explicit correction of sub-optimal actions, focusing instead on balancing exploration and exploitation to optimize performance over time.",,A type of machine learning focused on methods that do not require labeled input/output pairs or explicit correction of sub-optimal actions focusing instead on balancing exploration and exploitation to optimize performance over time.,A machine learning task focused on methods that do not require labeled input/output pairs or explicit correction of sub-optimal actions focusing instead on balancing exploration and exploitation to optimize performance over time.,https://en.wikipedia.org/wiki/Reinforcement_learning,,,AIO:MachineLearningTask
AIO:Clustering,AIO:MachineLearningSubset,Cluster analysis,,Clustering,FALSE,0.30,Methods that group a set of objects such that objects in the same group are more similar to each other than to those in other groups.,,A machine learning task focused on methods that group a set of objects such that objects in the same group are more similar to each other than to those in other groups.,A machine learning task focused on methods that group a set of objects such that objects in the same group are more similar to each other than to those in other groups.,https://en.wikipedia.org/wiki/Cluster_analysis,,,AIO:MachineLearningTask
AIO:ActiveLearning,AIO:MachineLearningSubset,Query Learning,,Active Learning,FALSE,0.33,Methods that interactively query a user or another information source to label new data points with the desired outputs.,,A type of machine learning focused on methods that interactively query a user or another information source to label new data points with the desired outputs.,A machine learning task focused on methods that interactively query a user or another information source to label new data points with the desired outputs.,https://en.wikipedia.org/wiki/Active_learning_(machine_learning),,,AIO:MachineLearningTask
AIO:SupervisedLearning,AIO:MachineLearningSubset,,,Supervised Learning,FALSE,0.38,Methods that learn a function mapping input to output based on example input-output pairs.,,A type of machine learning focused on methods that learn a function mapping input to output based on example input-output pairs.,A machine learning task focused on methods that learn a function mapping input to output based on example input-output pairs.,https://en.wikipedia.org/wiki/Supervised_learning,,,AIO:MachineLearningTask
AIO:TimeSeriesForecasting,AIO:MachineLearningSubset,,,Time Series Forecasting,FALSE,0.44,Methods that predict future values based on previously observed values.,Methods that predict future values based on previously observed values.,A machine learning task focused on methods that predict future values based on previously observed values.,A machine learning task focused on methods that predict future values based on previously observed values.,https://en.wikipedia.org/wiki/Time_series,,,AIO:MachineLearningTask
AIO:DataImputation,AIO:MachineLearningSubset,,,Data Imputation,FALSE,0.53,Methods that replace missing data with substituted values.,Methods that replace missing data with substituted values.,A machine learning task focused on methods that replace missing data with substituted values.,A machine learning task focused on methods that replace missing data with substituted values.,https://en.wikipedia.org/wiki/Imputation_(statistics),,,AIO:MachineLearningTask
AIO:Biclustering,AIO:MachineLearningSubset,Block Clustering|Co-clustering|Two-mode Clustering|Two-way Clustering|Joint Clustering,,Biclustering,FALSE,0.33,Methods that simultaneously cluster the rows and columns of a matrix to identify submatrices with coherent patterns.,,A machine learning task focused on methods that simultaneously cluster the rows and columns of a matrix to identify submatrices with coherent patterns.,A machine learning task focused on methods that simultaneously cluster the rows and columns of a matrix to identify submatrices with coherent patterns.,https://en.wikipedia.org/wiki/Biclustering,,,AIO:MachineLearningTask
AIO:EnsembleLearning,AIO:MachineLearningSubset,,,Ensemble Learning,FALSE,0.30,Methods that use multiple learning algorithms to achieve better predictive performance than any of the constituent algorithms alone.,,A type of machine learning focused on methods that use multiple learning algorithms to achieve better predictive performance than any of the constituent algorithms alone.,A machine learning task focused on methods that use multiple learning algorithms to achieve better predictive performance than any of the constituent algorithms alone.,https://en.wikipedia.org/wiki/Ensemble_learning,,,AIO:MachineLearningTask
AIO:NaturalLanguageProcessing,AIO:MachineLearningSubset,NLP,,Natural Language Processing,FALSE,0.28,"A subfield of linguistics, computer science, and artificial intelligence focused on the interactions between computers and human language, including programming computers to process and analyze large amounts of natural language data.",,A subfield of machine learning focused on the interactions between computers and human language including programming computers to process and analyze large amounts of natural language data.,A machine learning task focused on the interactions between computers and human language including programming computers to process and analyze large amounts of natural language data.,https://en.wikipedia.org/wiki/Natural_language_processing,,,AIO:MachineLearningTask
AIO:ProbabilisticGraphicalModel,AIO:MachineLearningSubset,PGM|Graphical Model|Structure Probabilistic Model,,Probabilistic Graphical Model,FALSE,0.18,A probabilistic model in which a graph expresses the conditional dependence structure between random variables.,,A machine learning model in which a graph expresses the conditional dependence structure between random variables.,A machine learning task in which a graph expresses the conditional dependence structure between random variables.,https://en.wikipedia.org/wiki/Graphical_model,,,AIO:MachineLearningTask
AIO:KnearestNeighborAlgorithm,AIO:MachineLearningSubset,KNN|K-NN,,K-nearest Neighbor Algorithm,FALSE,#N/A,,,"A machine learning that groups objects by a plurality vote of its neighbors, assigning each object to the class most common among its k nearest neighbors.","A machine learning task that groups objects by a plurality vote of its neighbors, assigning each object to the class most common among its k nearest neighbors.",https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm|,,,AIO:MachineLearningTask
AIO:SelfsupervisedLearning,AIO:MachineLearningSubset,,,Self-supervised Learning,FALSE,#N/A,,,A machine learning that is intermediate between supervised and unsupervised learning and predicts parts of the input data from other observed parts without relying on human-annotated labels.,A machine learning task that is intermediate between supervised and unsupervised learning and predicts parts of the input data from other observed parts without relying on human-annotated labels.,https://en.wikipedia.org/wiki/Self-supervised_learning|,,,AIO:MachineLearningTask
AIO:ProbabilisticTopicModel,AIO:MachineLearningSubset,,,Probabilistic Topic Model,FALSE,0.39,"Methods that use statistical techniques to analyze the words in each text to discover common themes, their connections, and their changes over time.",,A probabilistic graphical model that uses statistical techniques to analyze the words in each text to discover common themes their connections and their changes over time.,A probabilistic graphical model that uses statistical techniques to analyze the words in each text to discover common themes their connections and their changes over time.,https://pyro.ai/examples/prodlda.html|,,,AIO:ProbabilisticGraphicalModel
AIO:CausalGraphicalModel,AIO:MachineLearningSubset,Casaul Graph|Path Diagram|Casaul Bayesian Network|DAG|Directed Acyclic Graph,,Causal Graphical Model,FALSE,0.36,Probabilistic graphical models used to encode assumptions about the data-generating process.,,A probabilistic graphical model used to encode assumptions about the data-generating process.,A probabilistic graphical model used to encode assumptions about the data-generating process.,https://en.wikipedia.org/wiki/Causal_graph|,,,AIO:ProbabilisticGraphicalModel
AIO:ProportionalHazardsModel,AIO:MachineLearningSubset,,,Proportional Hazards Model,FALSE,0.17,A survival modeling method where the unique effect of a unit increase in a covariate is multiplicative with respect to the hazard rate.,,A regression analysis method for survival analysis where the unique effect of a unit increase in a covariate is multiplicative with respect to the hazard rate.,A regression analysis for survival analysis where the unique effect of a unit increase in a covariate is multiplicative with respect to the hazard rate.,https://en.wikipedia.org/wiki/Proportional_hazards_model,,,AIO:SurvivalAnalysis
AIO:FixedEffectsModel,AIO:MachineLearningSubset,FEM,,Fixed Effects Model,FALSE,0.21,A statistical model in which the model parameters are fixed or non-random quantities.,,A regression analysis model in which the model parameters are fixed or non-random quantities.,A regression analysis in which the model parameters are fixed or non-random quantities.,https://en.wikipedia.org/wiki/Fixed_effects_model|,,,AIO:RegressionAnalysis
AIO:RidgeRegression,AIO:MachineLearningSubset,,,Ridge Regression,FALSE,0.20,A method of estimating the coefficients of multiple regression models in scenarios where the independent variables are highly correlated.,,A regression analysis method that estimates the coefficients of multiple regression models in scenarios where the independent variables are highly correlated.,A regression analysis that estimates the coefficients of multiple regression models in scenarios where the independent variables are highly correlated.,https://en.wikipedia.org/wiki/Ridge_regression|,,,AIO:RegressionAnalysis
AIO:LogisticRegression,AIO:MachineLearningSubset,,,Logistic Regression,FALSE,0.12,A statistical model that estimates the probability of an event occurring by modeling the log-odds of the event as a linear combination of one or more independent variables.,,A regression analysis model that estimates the probability of an event occurring by modeling the log-odds of the event as a linear combination of one or more independent variables.,A regression analysis that estimates the probability of an event occurring by modeling the log-odds of the event as a linear combination of one or more independent variables.,https://en.wikipedia.org/wiki/Logistic_regression|,,,AIO:RegressionAnalysis
AIO:LinearRegression,AIO:MachineLearningSubset,,,Linear Regression,FALSE,0.23,A linear approach for modeling the relationship between a scalar response and one or more explanatory variables.,,A regression analysis model that is a linear approach for modeling the relationship between a scalar response and one or more explanatory variables.,A regression analysis that is a linear approach for modeling the relationship between a scalar response and one or more explanatory variables.,https://en.wikipedia.org/wiki/Linear_regression|,,,AIO:RegressionAnalysis
AIO:LassoRegression,AIO:MachineLearningSubset,,,Lasso Regression,FALSE,0.00,A regression analysis method that performs both variable selection and regularization to enhance prediction accuracy and interpretability.,,A regression analysis method that performs both variable selection and regularization to enhance prediction accuracy and interpretability.,A regression analysis that performs both variable selection and regularization to enhance prediction accuracy and interpretability.,https://en.wikipedia.org/wiki/Lasso_(statistics)|,,,AIO:RegressionAnalysis
AIO:GeneralizedLinearModel,AIO:MachineLearningSubset,GLM,,Generalized Linear Model,FALSE,0.07,A model that generalizes linear regression by relating the linear model to the response variable via a link function and allowing the variance of each measurement to be a function of its predicted value.,,A machine learning model that generalizes linear regression by relating the linear model to the response variable via a link function and allowing the variance of each measurement to be a function of its predicted value.,A regression analysis that relates the linear model to the response variable via a link function and allowing the variance of each measurement to be a function of its predicted value.,https://en.wikipedia.org/wiki/Generalized_linear_model|,,,AIO:RegressionAnalysis
AIO:SpatialRegression,AIO:MachineLearningSubset,,,Spatial Regression,FALSE,0.11,A regression method used to model spatial relationships.,,A regression analysis method used to model spatial relationships.,A regression analysis used to model spatial relationships.,https://gisgeography.com/spatial-regression-models-arcgis/|,,,AIO:RegressionAnalysis
AIO:RandomEffectsModel,AIO:MachineLearningSubset,REM,,Random Effects Model,FALSE,0.27,A statistical model where the model parameters are random variables.,,A regression analysis model where the model parameters are random variables.,A regression analysis where the model parameters are random variables.,https://en.wikipedia.org/wiki/Random_effects_model|,,,AIO:RegressionAnalysis
AIO:LeastsquaresAnalysis,AIO:MachineLearningSubset,,,Least-squares Analysis,FALSE,#N/A,,,A regression analysis which approximates the solution of overdetermined systems by minimizing the sum of the squares of the residuals.,A regression analysis which approximates the solution of overdetermined systems by minimizing the sum of the squares of the residuals.,https://en.wikipedia.org/wiki/Least_squares|,,,AIO:RegressionAnalysis
AIO:RegressionAnalysis,AIO:MachineLearningSubset,Regression analysis|Regression model,,Regression Analysis,FALSE,0.00,A set of statistical processes for estimating the relationships between a dependent variable and one or more independent variables.,,A set of statistical processes for estimating the relationships between a dependent variable and one or more independent variables.,A set of statistical processes for estimating the relationships between a dependent variable and one or more independent variables.,https://en.wikipedia.org/wiki/Regression_analysis|,,,AIO:SupervisedLearning
AIO:AssociationRuleLearning,AIO:MachineLearningSubset,,,Association Rule Learning,FALSE,0.32,A rule-based machine learning method for discovering interesting relations between variables in large databases.,,A supervised learning method focused on a rule-based approach for discovering interesting relations between variables in large databases.,A supervised learning focused on a rule-based approach for discovering interesting relations between variables in large databases.,https://en.wikipedia.org/wiki/Association_rule_learning|,,,AIO:SupervisedLearning
AIO:Classification,AIO:MachineLearningSubset,,,Classification,FALSE,0.44,"Methods that distinguish and distribute kinds of ""things"" into different groups.","Methods that distinguish and distribute kinds of ""things"" into different groups.","A supervised learning task focused on methods that distinguish and distribute kinds of ""things"" into different groups.","A supervised learning focused on methods that distinguish and distribute kinds of ""things"" into different groups.",https://en.wikipedia.org/wiki/Classification_(general_theory)|,,,AIO:SupervisedLearning
AIO:RandomForest,AIO:MachineLearningSubset,,,Random Forest,FALSE,0.19,"An ensemble learning method for classification, regression, and other tasks that constructs a multitude of decision trees during training.",,An ensemble learning method for classification regression and other tasks that constructs a multitude of decision trees during training.,An ensemble learning method for classification regression and other tasks that constructs a multitude of decision trees during training.,https://en.wikipedia.org/wiki/Random_forest,,,AIO:EnsembleLearning
AIO:KnearestNeighborRegressionAlgorithm,AIO:MachineLearningSubset,KNN Regression|K-NN Regression,,K-nearest Neighbor Regression Algorithm,FALSE,#N/A,,,An regression analysis that assigns the average of the values of k nearest neighbors to objects.,An regression analysis that assigns the average of the values of k nearest neighbors to objects.,https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm|,,,AIO:RegressionAnalysis
AIO:DimensionalityReduction,AIO:MachineLearningSubset,Dimension Reduction,,Dimensionality Reduction,FALSE,0.29,The process of transforming data from a high-dimensional space into a lower-dimensional space while retaining meaningful properties of the original data.,,A machine learning task focused on the process of transforming data from a high-dimensional space into a lower-dimensional space while retaining meaningful properties of the original data.,An unsupervised learning focused on the process of transforming data from a high-dimensional space into a lower-dimensional space while retaining meaningful properties of the original data.,https://en.wikipedia.org/wiki/Dimensionality_reduction|,,,AIO:UnsupervisedLearning
AIO:RecursiveLanguageModel,AIO:ModelSubset,RLM,Compositional generalization,Recursive Language Model,FALSE,0.14,"A recursive language model uses recursive neural network architectures like TreeLSTMs to learn syntactic composition functions, improving systematic generalization abilities.",,A language model that uses recursive neural network architectures like TreeLSTMs to learn syntactic composition functions improving systematic generalization abilities.,A deep neural network that uses recursive neural network architectures like TreeLSTMs to learn syntactic composition functions improving systematic generalization abilities.,https://en.wikipedia.org/wiki/Recurrent_neural_network,"Layers: Input, Memory Cell, Output",AIO:InputLayer|AIO:MemoryCellLayer|AIO:OutputLayer,AIO:DeepNeuralNetwork
AIO:LargeLanguageModel,AIO:ModelSubset,LLM,,Large Language Model,FALSE,0.07,"A language model consisting of a neural network with many parameters (typically billions of weights or more), trained on large quantities of unlabeled text using self-supervised learning or semi-supervised learning.",,A language model consisting of a neural network with many parameters (typically billions of weights or more) trained on large quantities of unlabeled text using self-supervised learning or semi-supervised learning.,A language model consisting of a neural network with many parameters (typically billions of weights or more) trained on large quantities of unlabeled text using self-supervised learning or semi-supervised learning.,https://en.wikipedia.org/wiki/Large_language_model,,,AIO:LanguageModel
AIO:ModularLanguageModel,AIO:ModelSubset,Modular LM,,Modular Language Model,FALSE,0.07,"A modular language model consists of multiple specialized components or skills that can be dynamically composed and recombined to solve complex tasks, mimicking the modular structure of human cognition.",,A language model that consists of multiple specialized components or skills that can be dynamically composed and recombined to solve complex tasks mimicking the modular structure of human cognition.,A language model that consists of multiple specialized components or skills that can be dynamically composed and recombined to solve complex tasks mimicking the modular structure of human cognition.,https://arxiv.org/abs/2302.11529v2,,,AIO:LanguageModel
AIO:GenerativeLanguageInterface,AIO:ModelSubset,,Interactive generation,Generative Language Interface,FALSE,0.23,"A generative language interface enables users to engage in an interactive dialogue with an LLM, providing feedback to guide and refine the generated outputs iteratively.",,A language model that enables users to engage in an interactive dialogue with an LLM providing feedback to guide and refine the generated outputs iteratively.,A language model that enables users to engage in an interactive dialogue with an LLM providing feedback to guide and refine the generated outputs iteratively.,,,,AIO:LanguageModel
AIO:AutoregressiveLanguageModel,AIO:ModelSubset,,generative language model|sequence-to-sequence model,Autoregressive Language Model,FALSE,0.28,"An autoregressive language model generates text sequentially, predicting one token at a time based on the previously generated tokens. It excels at natural language generation tasks by modeling the probability distribution over sequences of tokens.",,A language model that generates text sequentially predicting one token at a time based on the previously generated tokens excelling at natural language generation tasks by modeling the probability distribution over sequences of tokens.,A language model that generates text sequentially predicting one token at a time based on the previously generated tokens excelling at natural language generation tasks by modeling the probability distribution over sequences of tokens.,,,,AIO:LanguageModel
AIO:MaskedLanguageModel,AIO:ModelSubset,,bidirectional encoder|denoising autoencoder,Masked Language Model,FALSE,0.16,"A masked language model is trained to predict randomly masked tokens in a sequence, based on the remaining unmasked tokens. This allows it to build deep bidirectional representations that can be effectively transferred to various NLP tasks via fine-tuning.",,A language model that is trained to predict randomly masked tokens in a sequence based on the remaining unmasked tokens allowing it to build deep bidirectional representations that can be effectively transferred to various NLP tasks via fine-tuning.,A language model that is trained to predict randomly masked tokens in a sequence based on the remaining unmasked tokens allowing it to build deep bidirectional representations that can be effectively transferred to various NLP tasks via fine-tuning.,,,,AIO:LanguageModel
AIO:MultimodalLanguageModel,AIO:ModelSubset,Mulimodal LM,,Multimodal Language Model,FALSE,0.22,"A multimodal language model learns joint representations across different modalities like text, vision, and audio in an end-to-end fashion for better cross-modal understanding and generation.",,A language model that learns joint representations across different modalities like text vision and audio in an end-to-end fashion for better cross-modal understanding and generation.,A language model that learns joint representations across different modalities like text vision and audio in an end-to-end fashion for better cross-modal understanding and generation.,https://arxiv.org/abs/2205.12630,,,AIO:LanguageModel
AIO:GraphLanguageModel,AIO:ModelSubset,Graph LM,Structured representations,Graph Language Model,FALSE,0.17,"A graph language model operates over structured inputs or outputs represented as graphs, enabling reasoning over explicit relational knowledge representations during language tasks.",,A language model that operates over structured inputs or outputs represented as graphs enabling reasoning over explicit relational knowledge representations during language tasks.,A language model that operates over structured inputs or outputs represented as graphs enabling reasoning over explicit relational knowledge representations during language tasks.,https://arxiv.org/abs/2401.07105,,,AIO:LanguageModel
AIO:HierarchicalLanguageModel,AIO:ModelSubset,Hierarchical LM,multi-scale representations,Hierarchical Language Model,FALSE,0.10,"A hierarchical language model represents language at multiple levels of granularity, learning hierarchical representations that capture both low-level patterns and high-level abstractions.",,A language model that represents language at multiple levels of granularity learning hierarchical representations that capture both low-level patterns and high-level abstractions.,A language model that represents language at multiple levels of granularity learning hierarchical representations that capture both low-level patterns and high-level abstractions.,https://doi.org/10.1016/j.ipm.2024.103698,,,AIO:LanguageModel
AIO:ImplicitLanguageModel,AIO:ModelSubset,Implicit LM,Energy-based models|Token-level scoring,Implicit Language Model,FALSE,0.22,"An implicit language model uses an energy function to score entire sequences instead of factorizing probabilities autoregressively, better capturing global properties and long-range dependencies.",,A language model that uses an energy function to score entire sequences instead of factorizing probabilities autoregressively better capturing global properties and long-range dependencies.,A language model that uses an energy function to score entire sequences instead of factorizing probabilities autoregressively better capturing global properties and long-range dependencies.,https://arxiv.org/pdf/2303.16189,,,AIO:LanguageModel
AIO:RecursiveLLM,AIO:ModelSubset,Recursive Large Language Model|Self-Attending Large Language Model,self-attention|iterative refinement,Recursive LLM,FALSE,0.18,"A recursive language model uses recursive neural network architectures like TreeLSTMs to learn syntactic composition functions, improving systematic generalization abilities.",,A large language model that uses recursive neural network architectures like TreeLSTMs to learn syntactic composition functions improving systematic generalization abilities.,A language model that uses recursive neural network architectures like TreeLSTMs to learn syntactic composition functions improving systematic generalization abilities.,https://doi.org/10.1609/aaai.v33i01.33017450,,,AIO:LanguageModel
AIO:TransformerLanguageModel,AIO:ModelSubset,Transformer LM,,Transformer Language Model,FALSE,0.19,"A transformer LM is a neural network model that uses the transformer architecture based on multi-head attention mechanisms, allowing it to contextualize tokens within a context window for effective language understanding and generation.",,A language model that uses the transformer architecture based on multi-head attention mechanisms allowing it to contextualize tokens within a context window for effective language understanding and generation.,A language model that uses the transformer architecture based on multi-head attention mechanisms allowing it to contextualize tokens within a context window for effective language understanding and generation.,https://arxiv.org/abs/1706.03762,,,AIO:LanguageModel
AIO:FactoredLanguageModel,AIO:ModelSubset,Factorized Language Model,,Factored Language Model,FALSE,0.38,"A factored language model views each word as a vector of multiple factors, such as part-of-speech, morphology, and semantics, to improve language modeling.",,A language model that views each word as a vector of multiple factors such as part-of-speech morphology and semantics to improve language modeling.,A language model that views each word as a vector of multiple factors such as part-of-speech morphology and semantics to improve language modeling.,https://en.wikipedia.org/wiki/Factored_language_model,,,AIO:LanguageModel
AIO:EncoderDecoderLLM,AIO:ModelSubset,,,Encoder-Decoder LLM,FALSE,#N/A,,,"The LLM introduced in the ""Attention Is All You Need"" paper. The encoder processes the input sequence to generate a hidden representation summarizing the input information, while the decoder uses this hidden representation to generate the desired output sequence.","A large language model introduced in the ""Attention Is All You Need"" paper. The encoder processes the input sequence to generate a hidden representation summarizing the input information, while the decoder uses this hidden representation to generate the desired output sequence.",https://www.practicalai.io/understanding-transformer-model-architectures/#:~:text=Encoder,,,AIO:LargeLanguageModel
AIO:PersonalizedLLM,AIO:ModelSubset,Personalized Large Language Model,user adaptation LLM,Personalized LLM,FALSE,0.38,"A personalized LLM adapts its language modeling and generation to the preferences, style, and persona of individual users or audiences.",,A large language model that adapts its language modeling and generation to the preferences style and persona of individual users or audiences.,A large language model that adapts its language modeling and generation to the preferences style and persona of individual users or audiences.,,,,AIO:LargeLanguageModel
AIO:ControllableLLM,AIO:ModelSubset,Controllable Large Language Model,conditional generation|guided generation,Controllable LLM,FALSE,0.43,"A controllable LLM allows for explicit control over certain attributes of the generated text, such as style, tone, topic, or other desired characteristics, through conditioning or specialized training objectives.","A controllable LLM allows for explicit control over certain attributes of the generated text, such as style, tone, topic, or other desired characteristics, through conditioning or specialized training objectives.",A large language model that allows for explicit control over certain attributes of the generated text such as style tone topic or other desired characteristics through conditioning or specialized training objectives.,A large language model that allows for explicit control over certain attributes of the generated text such as style tone topic or other desired characteristics through conditioning or specialized training objectives.,,,,AIO:LargeLanguageModel
AIO:EvolutionaryLLM,AIO:ModelSubset,Evolutionary Language Model,evolutionary algorithms|genetic programming,Evolutionary LLM,FALSE,0.38,"An evolutionary LLM applies principles of evolutionary computation to optimize its structure and parameters, evolving over time to improve performance.",,A large language model that applies principles of evolutionary computation to optimize its structure and parameters evolving over time to improve performance.,A large language model that applies principles of evolutionary computation to optimize its structure and parameters evolving over time to improve performance.,,,,AIO:LargeLanguageModel
AIO:ContinualLearningLLM,AIO:ModelSubset,CL-Large Language Model|Continual Learning Large Language Model,lifelong learning|catastrophic forgetting,Continual Learning LLM,FALSE,0.31,A continual learning LLM continually acquires new knowledge and skills over time without forgetting previously learned information. This allows the model to adapt and expand its capabilities as new data becomes available.,,A large language model that continually acquires new knowledge and skills over time without forgetting previously learned information allowing the model to adapt and expand its capabilities as new data becomes available.,A large language model that continually acquires new knowledge and skills over time without forgetting previously learned information allowing the model to adapt and expand its capabilities as new data becomes available.,,,,AIO:LargeLanguageModel
AIO:LifelongLearningLLM,AIO:ModelSubset,Continual Learning LLM|Forever Learning,Catastrophic forgetting|Plasticity-Stability balance,Lifelong Learning LLM,FALSE,0.33,"A lifelong learning LLM continually acquires new knowledge over time without forgetting previously learned information, maintaining a balance between plasticity and stability.",,A large language model that continually acquires new knowledge over time without forgetting previously learned information maintaining a balance between plasticity and stability.,A large language model that continually acquires new knowledge over time without forgetting previously learned information maintaining a balance between plasticity and stability.,,,,AIO:LargeLanguageModel
AIO:FactorizedLLM,AIO:ModelSubset,Factorized Large Language Model|Factorized Learning Assisted with Large Language Model,Conditional masking|Product of experts,Factorized LLM,FALSE,0.21,"A factorized LLM decomposes the full language modeling task into multiple sub-components or experts that each focus on a subset of the information, enabling more efficient scaling.",,A large language model that decomposes the full language modeling task into multiple sub-components or experts that each focus on a subset of the information enabling more efficient scaling.,A large language model that decomposes the full language modeling task into multiple sub-components or experts that each focus on a subset of the information enabling more efficient scaling.,https://doi.org/10.48550/arXiv.2403.12556,,,AIO:LargeLanguageModel
AIO:DatatoTextLLM,AIO:ModelSubset,Meaning representation,,Data-to-Text LLM,FALSE,#N/A,,,"A LLM that generates natural language descriptions from structured data sources like tables, graphs, and knowledge bases, requiring grounding in meaning representations.","A large language model that generates natural language descriptions from structured data sources like tables, graphs, and knowledge bases, requiring grounding in meaning representations.",,,,AIO:LargeLanguageModel
AIO:DifferentiableLLM,AIO:ModelSubset,Differentiable Large Language Model,end-to-end training|fully backpropagable,Differentiable LLM,FALSE,0.31,"A differentiable LLM has an architecture amenable to full end-to-end training via backpropagation, without relying on teacher forcing or unlikelihood training objectives.",,A large language model that has an architecture amenable to full end-to-end training via backpropagation without relying on teacher forcing or unlikelihood training objectives.,A large language model that has an architecture amenable to full end-to-end training via backpropagation without relying on teacher forcing or unlikelihood training objectives.,,,,AIO:LargeLanguageModel
AIO:ReasoningLLM,AIO:ModelSubset,Reasoning Large Language Model|Rational Large Language Model,reasoning|logical inferences,Reasoning LLM,FALSE,0.38,"A reasoning LLM incorporates explicit reasoning capabilities, leveraging logical rules, axioms, or external knowledge to make deductive inferences during language tasks.",,A large language model that incorporates explicit reasoning capabilities leveraging logical rules axioms or external knowledge to make deductive inferences during language tasks.,A large language model that incorporates explicit reasoning capabilities leveraging logical rules axioms or external knowledge to make deductive inferences during language tasks.,https://doi.org/10.18653/v1/2023.acl-long.347,,,AIO:LargeLanguageModel
AIO:EmbodiedLLM,AIO:ModelSubset,Embodied Large Language Model,multimodal grounding,Embodied LLM,FALSE,0.42,"An embodied LLM integrates language with other modalities like vision, audio, and robotics to enable grounded language understanding in real-world environments.","An embodied LLM integrates language with other modalities like vision, audio, and robotics to enable grounded language understanding in real-world environments.",A large language model that integrates language with other modalities like vision audio and robotics to enable grounded language understanding in real-world environments.,A large language model that integrates language with other modalities like vision audio and robotics to enable grounded language understanding in real-world environments.,,,,AIO:LargeLanguageModel
AIO:ExplainableLLM,AIO:ModelSubset,Explainable Language Model|XAI LLM,interpretability|model understanding,Explainable LLM,FALSE,0.39,"An explainable LLM is designed to provide insights into its decision-making process, making it easier for users to understand and trust the model's outputs. It incorporates mechanisms for interpreting and explaining its predictions in human-understandable terms.",,A large language model that is designed to provide insights into its decision-making process making it easier for users to understand and trust the model's outputs by incorporating mechanisms for interpreting and explaining its predictions in human-understandable terms.,A large language model that is designed to provide insights into its decision-making process making it easier for users to understand and trust the model's outputs by incorporating mechanisms for interpreting and explaining its predictions in human-understandable terms.,,,,AIO:LargeLanguageModel
AIO:ReinforcementLearningLLM,AIO:ModelSubset,RL-Large Language Model|Reinforcement Learning Large Language Model,reward modeling|decision transformers,Reinforcement Learning LLM,FALSE,0.43,"An RL-LLM is a language model fine-tuned using reinforcement learning, where the model receives rewards for generating text that satisfies certain desired properties or objectives. This can improve the quality, safety, or alignment of generated text.","An RL-LLM is a language model fine-tuned using reinforcement learning, where the model receives rewards for generating text that satisfies certain desired properties or objectives. This can improve the quality, safety, or alignment of generated text.",A large language model that is fine-tuned using reinforcement learning where the model receives rewards for generating text that satisfies certain desired properties or objectives improving the quality safety or alignment of generated text.,A large language model that is fine-tuned using reinforcement learning where the model receives rewards for generating text that satisfies certain desired properties or objectives improving the quality safety or alignment of generated text.,,,,AIO:LargeLanguageModel
AIO:DialogueLLM,AIO:ModelSubset,Dialogue Large Language Model,conversational AI|multi-turn dialogue,Dialogue LLM,FALSE,0.39,"A dialogue LLM is optimized for engaging in multi-turn conversations, understanding context, and generating relevant, coherent responses continuously over many dialogue turns.",,A large language model that is optimized for engaging in multi-turn conversations understanding context and generating relevant coherent responses continuously over many dialogue turns.,A large language model that is optimized for engaging in multi-turn conversations understanding context and generating relevant coherent responses continuously over many dialogue turns.,,,,AIO:LargeLanguageModel
AIO:CurriculumLearningLLM,AIO:ModelSubset,,Learning progression,Curriculum Learning LLM,FALSE,0.30,"A curriculum learning LLM is trained by presenting learning examples in a meaningful order from simple to complex, mimicking the learning trajectory followed by humans.",,A large language model that is trained by presenting learning examples in a meaningful order from simple to complex mimicking the learning trajectory followed by humans.,A large language model that is trained by presenting learning examples in a meaningful order from simple to complex mimicking the learning trajectory followed by humans.,,,,AIO:LargeLanguageModel
AIO:FederatedLLM,AIO:ModelSubset,Federated Large Language Model,privacy-preserving|decentralized training,Federated LLM,FALSE,0.34,"A federated LLM is trained in a decentralized manner across multiple devices or silos, without directly sharing private data. This enables collaborative training while preserving data privacy and security.",,A large language model that is trained in a decentralized manner across multiple devices or silos without directly sharing private data enabling collaborative training while preserving data privacy and security.,A large language model that is trained in a decentralized manner across multiple devices or silos without directly sharing private data enabling collaborative training while preserving data privacy and security.,,,,AIO:LargeLanguageModel
AIO:MultilingualLLM,AIO:ModelSubset,Multilingual Large Language Model,cross-lingual transfer,Multilingual LLM,FALSE,0.27,"A multilingual LLM is trained on text from multiple languages, learning shared representations that enable zero-shot or few-shot transfer to new languages.",,A large language model that is trained on text from multiple languages learning shared representations that enable zero-shot or few-shot transfer to new languages.,A large language model that is trained on text from multiple languages learning shared representations that enable zero-shot or few-shot transfer to new languages.,,,,AIO:LargeLanguageModel
AIO:UnsupervisedLLM,AIO:ModelSubset,Unsupervised Large Language Model,self-supervised,Unsupervised LLM,FALSE,0.36,"An unsupervised LLM is trained solely on unlabeled data using self-supervised objectives like masked language modeling, without any supervised fine-tuning.",,A large language model that is trained solely on unlabeled data using self-supervised objectives like masked language modeling without any supervised fine-tuning.,A large language model that is trained solely on unlabeled data using self-supervised objectives like masked language modeling without any supervised fine-tuning.,,,,AIO:LargeLanguageModel
AIO:OrdinalLLM,AIO:ModelSubset,Ordinal Large Language Model,ranking|preference modeling,Ordinal LLM,FALSE,0.33,"An ordinal LLM is trained to model ordinal relationships and rank outputs, rather than model probability distributions over text sequences directly.",,A large language model that is trained to model ordinal relationships and rank outputs rather than model probability distributions over text sequences directly.,A large language model that is trained to model ordinal relationships and rank outputs rather than model probability distributions over text sequences directly.,,,,AIO:LargeLanguageModel
AIO:ContrastiveLearningLLM,AIO:ModelSubset,,Representation learning,Contrastive Learning LLM,FALSE,0.25,"A contrastive learning LLM is trained to pull semantically similar samples closer together and push dissimilar samples apart in the representation space, learning high-quality features useful for downstream tasks.",,A large language model that is trained to pull semantically similar samples closer together and push dissimilar samples apart in the representation space learning high-quality features useful for downstream tasks.,A large language model that is trained to pull semantically similar samples closer together and push dissimilar samples apart in the representation space learning high-quality features useful for downstream tasks.,,,,AIO:LargeLanguageModel
AIO:GenerativeCommonsenseLLM,AIO:ModelSubset,Generative Commonsense Large Language Model|World Model,physical reasoning|causal modeling,Generative Commonsense LLM,FALSE,0.38,"A generative commonsense LLM is trained to understand and model basic physics, causality, and common sense about how the real world works.",,A large language model that is trained to understand and model basic physics causality and common sense about how the real world works.,A large language model that is trained to understand and model basic physics causality and common sense about how the real world works.,https://arxiv.org/abs/2306.12672,,,AIO:LargeLanguageModel
AIO:CompositionalGeneralizationLLM,AIO:ModelSubset,Compositional Generalization Large Language Model,systematic generalization|out-of-distribution generalization,Compositional Generalization LLM,FALSE,0.24,"A compositional generalization LLM is trained to understand and recombine the underlying compositional structures in language, enabling better generalization to novel combinations and out-of-distribution examples.",,A large language model that is trained to understand and recombine the underlying compositional structures in language enabling better generalization to novel combinations and out-of-distribution examples.,A large language model that is trained to understand and recombine the underlying compositional structures in language enabling better generalization to novel combinations and out-of-distribution examples.,,,,AIO:LargeLanguageModel
AIO:EthicalLLM,AIO:ModelSubset,Ethical Large Language Model,value alignment|constituitional AI,Ethical LLM,FALSE,0.38,"An ethical LLM is trained to uphold certain ethical principles, values, or rules in its language generation to increase safety and trustworthiness.",,A large language model that is trained to uphold certain ethical principles values or rules in its language generation to increase safety and trustworthiness.,A large language model that is trained to uphold certain ethical principles values or rules in its language generation to increase safety and trustworthiness.,,,,AIO:LargeLanguageModel
AIO:MultimodalFusionLLM,AIO:ModelSubset,,cross-modal grounding,Multimodal Fusion LLM,FALSE,0.37,"A multimodal fusion LLM learns joint representations across different modalities like text, vision, and audio in an end-to-end fashion for better cross-modal understanding and generation.",,A large language model that learns joint representations across different modalities like text vision and audio in an end-to-end fashion for better cross-modal understanding and generation.,A large language model that learns joint representations across different modalities like text vision and audio in an end-to-end fashion for better cross-modal understanding and generation.,,,,AIO:LargeLanguageModel
AIO:TransferLearningLLM,AIO:ModelSubset,Transfer LLM,transfer learning,Transfer Learning LLM,FALSE,0.28,"A transfer learning LLM leverages knowledge acquired during training on one task to improve performance on different but related tasks, facilitating more efficient learning and adaptation.",,A large language model that leverages knowledge acquired during training on one task to improve performance on different but related tasks facilitating more efficient learning and adaptation.,A large language model that leverages knowledge acquired during training on one task to improve performance on different but related tasks facilitating more efficient learning and adaptation.,,,,AIO:LargeLanguageModel
AIO:CausalLLM,AIO:ModelSubset,Causal Large Language Model,unidirectional|autoregressive,Causal LLM,FALSE,0.30,"A causal LLM only attends to previous tokens in the sequence when generating text, modeling the probability distribution autoregressively from left-to-right or causally.",,A large language model that only attends to previous tokens in the sequence when generating text modeling the probability distribution autoregressively from left-to-right or causally.,A large language model that only attends to previous tokens in the sequence when generating text modeling the probability distribution autoregressively from left-to-right or causally.,,,,AIO:LargeLanguageModel
AIO:CrossDomainLLM,AIO:ModelSubset,Domain-General LLM,domain adaptation|cross-domain transfer,Cross-Domain LLM,FALSE,#N/A,,,"A LLM that performs well across a wide range of domains without significant loss in performance, facilitated by advanced domain adaptation techniques.","A large language model that performs well across a wide range of domains without significant loss in performance, facilitated by advanced domain adaptation techniques.",,,,AIO:LargeLanguageModel
AIO:LanguageInterfaceLLM,AIO:ModelSubset,,Interactive learning,Language Interface LLM,FALSE,0.29,"A language interface LLM supports interactive semantic parsing, enabling users to provide feedback and corrections to dynamically refine and update the language model.",,A large language model that supports interactive semantic parsing enabling users to provide feedback and corrections to dynamically refine and update the language model.,A large language model that supports interactive semantic parsing enabling users to provide feedback and corrections to dynamically refine and update the language model.,,,,AIO:LargeLanguageModel
AIO:DecoderLLM,AIO:ModelSubset,,,Decoder LLM,FALSE,0.62,"A decoder-only architecture consisting of only a decoder, trained to predict the next token in a sequence given the previous tokens. Unlike the encoder-decoder architecture, it does not have an explicit encoder and encodes information implicitly in the hidden state of the decoder, updated at each step of the generation process.","A decoder-only architecture consisting of only a decoder, trained to predict the next token in a sequence given the previous tokens. Unlike the encoder-decoder architecture, it does not have an explicit encoder and encodes information implicitly in the hidden state of the decoder, updated at each step of the generation process.",A large language model that uses a decoder-only architecture consisting of only a decoder trained to predict the next token in a sequence given the previous tokens.,A large language model that uses a decoder-only architecture consisting of only a decoder trained to predict the next token in a sequence given the previous tokens.,https://www.practicalai.io/understanding-transformer-model-architectures/#:~:text=Encoder,,,AIO:LargeLanguageModel
AIO:EncoderLLM,AIO:ModelSubset,,,Encoder LLM,FALSE,0.48,"An encoder-only architecture that encodes the input sequence into a fixed-length representation, which is then used as input to a classifier or regressor for prediction. The model has a pre-trained general-purpose encoder that requires fine-tuning for specific tasks.","An encoder-only architecture that encodes the input sequence into a fixed-length representation, which is then used as input to a classifier or regressor for prediction. The model has a pre-trained general-purpose encoder that requires fine-tuning for specific tasks.",A large language model that uses an encoder-only architecture to encode the input sequence into a fixed-length representation which is then used as input to a classifier or regressor for prediction.,A large language model that uses an encoder-only architecture to encode the input sequence into a fixed-length representation which is then used as input to a classifier or regressor for prediction.,https://www.practicalai.io/understanding-transformer-model-architectures/#:~:text=Encoder,,,AIO:LargeLanguageModel
AIO:SparseLLM,AIO:ModelSubset,Sparse Large Language Model,model compression|parameter efficiency,Sparse LLM,FALSE,0.22,"A sparse LLM uses techniques like pruning or quantization to reduce the number of non-zero parameters in the model, making it more parameter-efficient and easier to deploy on resource-constrained devices.",,A large language model that uses techniques like pruning or quantization to reduce the number of non-zero parameters in the model making it more parameter-efficient and easier to deploy on resource-constrained devices.,A large language model that uses techniques like pruning or quantization to reduce the number of non-zero parameters in the model making it more parameter-efficient and easier to deploy on resource-constrained devices.,,,,AIO:LargeLanguageModel
AIO:RetrievalAugmentedLLM,AIO:ModelSubset,Retrieval-Augmented Large Language Model,knowledge grounding|open-book question answering,Retrieval-Augmented LLM,FALSE,#N/A,,,"A LLM which combines a pre-trained language model with a retrieval system that can access external knowledge sources. This allows the model to condition its generation on relevant retrieved knowledge, improving factual accuracy and knowledge grounding.","A large language model which combines a pre-trained language model with a retrieval system that can access external knowledge sources. This allows the model to condition its generation on relevant retrieved knowledge, improving factual accuracy and knowledge grounding.",,,,AIO:LargeLanguageModel
AIO:NeuroSymbolicLLM,AIO:ModelSubset,Neuro-Symbolic Large Language Model,knowledge reasoning|symbolic grounding,Neuro-Symbolic LLM,FALSE,#N/A,,,"A LLM which combines neural language modeling with symbolic reasoning components, leveraging structured knowledge representations and logical inferences to improve reasoning capabilities.","A large language model which combines neural language modeling with symbolic reasoning components, leveraging structured knowledge representations and logical inferences to improve reasoning capabilities.",,,,AIO:LargeLanguageModel
AIO:SemiSupervisedLLM,AIO:ModelSubset,Semi-Supervised Large Language Model,self-training,Semi-Supervised LLM,FALSE,#N/A,,,A LLM which combines self-supervised pretraining on unlabeled data with supervised fine-tuning on labeled task data.,A large language model which combines self-supervised pretraining on unlabeled data with supervised fine-tuning on labeled task data.,,,,AIO:LargeLanguageModel
AIO:MixtureofExpertsLLM,AIO:ModelSubset,MoE Large Language Model|Mixture-of-Experts Large Language Model,conditional computation|model parallelism,Mixture-of-Experts LLM,FALSE,#N/A,,,"A LLM which dynamically selects and combines outputs from multiple expert submodels, allowing for efficient scaling by conditionally activating only a subset of model components for each input.","A large language model which dynamically selects and combines outputs from multiple expert submodels, allowing for efficient scaling by conditionally activating only a subset of model components for each input.",https://proceedings.mlr.press/v162/du22c.html,,,AIO:LargeLanguageModel
AIO:GenerativeAdversarialNetworkAugmentedLLM,AIO:ModelSubset,GAN-Large Language Model|Generative Adversarial Network-Augmented Large Language Model,text generation|adversarial training,Generative Adversarial Network-Augmented LLM,FALSE,#N/A,,,"A LLM which incorporates a generative adversarial network (GAN) into its training process, using a discriminator network to provide a signal for generating more realistic and coherent text. This adversarial training can improve the quality and diversity of generated text.","A large language model which incorporates a generative adversarial network (GAN) into its training process, using a discriminator network to provide a signal for generating more realistic and coherent text. This adversarial training can improve the quality and diversity of generated text.",,,,AIO:LargeLanguageModel
AIO:KnowledgeGroundedLLM,AIO:ModelSubset,Knowledge-Grounded Large Language Model,factual grounding|knowledge integration,Knowledge-Grounded LLM,FALSE,#N/A,,,"A LLM which incorporates external knowledge sources or knowledge bases into the model architecture, enabling it to generate more factually accurate and knowledge-aware text.","A large language model which incorporates external knowledge sources or knowledge bases into the model architecture, enabling it to generate more factually accurate and knowledge-aware text.",,,,AIO:LargeLanguageModel
AIO:MemoryAugmentedLLM,AIO:ModelSubset,Memory-Augmented Large Language Model,external memory,Memory-Augmented LLM,FALSE,#N/A,,,"A LLM which incorporates external writable and readable memory components, allowing it to store and retrieve information over long contexts.","A large language model which incorporates external writable and readable memory components, allowing it to store and retrieve information over long contexts.",https://arxiv.org/abs/2306.07174,,,AIO:LargeLanguageModel
AIO:PromptbasedFineTuningLLM,AIO:ModelSubset,Prompt-tuned Large Language Model|Prompt-based Fine-Tuning Large Language Model,in-context learning|few-shot learning,Prompt-based Fine-Tuning LLM,FALSE,#N/A,,,"A LLM which is fine-tuned on a small number of examples or prompts, rather than full task datasets. This allows for rapid adaptation to new tasks with limited data, leveraging the model's few-shot learning capabilities.","A large language model which is fine-tuned on a small number of examples or prompts, rather than full task datasets. This allows for rapid adaptation to new tasks with limited data, leveraging the model's few-shot learning capabilities.",,,,AIO:LargeLanguageModel
AIO:InstructionTunedLLM,AIO:ModelSubset,Instruction-Tuned Large Language Model,natural language instructions|constitutional AI,Instruction-Tuned LLM,FALSE,#N/A,,,"A LLM which is fine-tuned to follow natural language instructions accurately and safely, learning to map from instructions to desired model behavior in a more controlled and principled way.","A large language model which is fine-tuned to follow natural language instructions accurately and safely, learning to map from instructions to desired model behavior in a more controlled and principled way.",,,,AIO:LargeLanguageModel
AIO:LowResourceLLM,AIO:ModelSubset,Low-Resource Language Model,resource-efficient|low-resource languages,Low-Resource LLM,FALSE,#N/A,,,"A LLM which is optimized for performance in scenarios with limited data, computational resources, or for languages with sparse datasets.","A large language model which is optimized for performance in scenarios with limited data, computational resources, or for languages with sparse datasets.",,,,AIO:LargeLanguageModel
AIO:DomainAdaptedLLM,AIO:ModelSubset,Domain-Adapted Large Language Model,transfer learning|domain robustness,Domain-Adapted LLM,FALSE,#N/A,,,"A LLM which is pre-trained on a broad corpus and then fine-tuned on domain-specific data to specialize its capabilities for particular domains or applications, like scientific literature or code generation.","A large language model which is pre-trained on a broad corpus and then fine-tuned on domain-specific data to specialize its capabilities for particular domains or applications, like scientific literature or code generation.",,,,AIO:LargeLanguageModel
AIO:MetaLearningLLM,AIO:ModelSubset,Meta-Learning Large Language Model,few-shot adaptation|learning to learn,Meta-Learning LLM,FALSE,#N/A,,,"A LLM which is trained in a way that allows it to quickly adapt to new tasks or datasets through only a few examples or fine-tuning steps, leveraging meta-learned priors about how to efficiently learn.","A large language model which is trained in a way that allows it to quickly adapt to new tasks or datasets through only a few examples or fine-tuning steps, leveraging meta-learned priors about how to efficiently learn.",,,,AIO:LargeLanguageModel
AIO:MultiTaskLLM,AIO:ModelSubset,Multi-Task Large Language Model,transfer learning,Multi-Task LLM,FALSE,#N/A,,,"A LLM which is trained jointly on multiple language tasks simultaneously, learning shared representations that transfer across tasks.","A large language model which is trained jointly on multiple language tasks simultaneously, learning shared representations that transfer across tasks.",,,,AIO:LargeLanguageModel
AIO:SelfSupervisedLLM,AIO:ModelSubset,,Pretext tasks,Self-Supervised LLM,FALSE,#N/A,,,"A LLM which learns rich representations by solving pretext tasks that involve predicting parts of the input from other observed parts of the data, without relying on human-annotated labels.","A large language model which learns rich representations by solving pretext tasks that involve predicting parts of the input from other observed parts of the data, without relying on human-annotated labels.",,,,AIO:LargeLanguageModel
AIO:EnergyBasedLLM,AIO:ModelSubset,Energy-Based Large Language Model,energy scoring|explicit density modeling,Energy-Based LLM,FALSE,#N/A,,,"A LLM which models the explicit probability density over token sequences using an energy function, rather than an autoregressive factorization. This can improve modeling of long-range dependencies and global coherence.","A large language model which models the explicit probability density over token sequences using an energy function, rather than an autoregressive factorization. This can improve modeling of long-range dependencies and global coherence.",,,,AIO:LargeLanguageModel
AIO:ZeroShotLearningLLM,AIO:ModelSubset,Zero-Shot LLM,zero-shot learning,Zero-Shot Learning LLM,FALSE,#N/A,,,"A LLM which performs tasks or understands concepts it has not explicitly been trained on, demonstrating a high degree of generalization and understanding.","A large language model which performs tasks or understands concepts it has not explicitly been trained on, demonstrating a high degree of generalization and understanding.",,,,AIO:LargeLanguageModel
AIO:LanguageModel,AIO:ModelSubset,,,Language Model,FALSE,0.09,A language model is a probabilistic model designed to predict the next word in a sequence or assign probabilities to sequences of words in natural language.,,A model designed to predict the next word in a sequence or assign probabilities to sequences of words in natural language.,A model designed to predict the next word in a sequence or assign probabilities to sequences of words in natural language.,https://en.wikipedia.org/wiki/Language_model,,,AIO:Model
AIO:ThresholdAutoregressive,AIO:ModelSubset,TAR,,Threshold Autoregressive,FALSE,#N/A,,,"A model that allows for different autoregressive processes depending on the regime or state of the time series, enabling the capture of nonlinear behaviors.","A model that allows for different autoregressive processes depending on the regime or state of the time series, enabling the capture of nonlinear behaviors.",https://dx.doi.org/10.1080/01621459.1989.10478760,,,AIO:Model
AIO:DynamicConditionalCorrelation,AIO:ModelSubset,DCC,,Dynamic Conditional Correlation,FALSE,#N/A,,,"A model that allows for time-varying correlations between different time series, used in financial econometrics to model and forecast covariances.","A model that allows for time-varying correlations between different time series, used in financial econometrics to model and forecast covariances.",,,,AIO:Model
AIO:VectorAutoregression,AIO:ModelSubset,VAR,,Vector Autoregression,FALSE,#N/A,,,"A model that captures the linear interdependencies among multiple time series, where each variable is modeled as a linear function of its own past values and the past values of all other variables in the system.","A model that captures the linear interdependencies among multiple time series, where each variable is modeled as a linear function of its own past values and the past values of all other variables in the system.",,,,AIO:Model
AIO:AutoregressiveMovingAverage,AIO:ModelSubset,ARMA,,Autoregressive Moving Average,FALSE,#N/A,,,"A model that combines autoregressive (AR) and moving average (MA) components to represent time series data, suitable for stationary series without the need for differencing.","A model that combines autoregressive (AR) and moving average (MA) components to represent time series data, suitable for stationary series without the need for differencing.",,,,AIO:Model
AIO:ExponentialSmoothingStateSpaceModel,AIO:ModelSubset,ETS,,Exponential Smoothing State Space Model,FALSE,#N/A,,,"A model that combines exponential smoothing with state space modeling, allowing for the inclusion of both trend and seasonal components. Used in  forecasting.","A model that combines exponential smoothing with state space modeling, allowing for the inclusion of both trend and seasonal components. Used in  forecasting.",,,,AIO:Model
AIO:AutoregressiveConditionalHeteroskedasticity,AIO:ModelSubset,ARCH,,Autoregressive Conditional Heteroskedasticity,FALSE,#N/A,,,"A model that describes the variance of the current error term as a function of the previous periods' error terms, capturing volatility clustering. Used for time series data.","A model that describes the variance of the current error term as a function of the previous periods' error terms, capturing volatility clustering. Used for time series data.",,,,AIO:Model
AIO:SeasonalAutoregressiveIntegratedMovingAverage,AIO:ModelSubset,SARIMA,,Seasonal Autoregressive Integrated Moving-Average,FALSE,#N/A,,,"A model that extends ARIMA, explicitly supporting univariate time series data with a seasonal component, combining seasonal differencing with ARIMA modeling.","A model that extends ARIMA, explicitly supporting univariate time series data with a seasonal component, combining seasonal differencing with ARIMA modeling.",,,,AIO:Model
AIO:AutoregressiveDistributedLag,AIO:ModelSubset,ARDL,,Autoregressive Distributed Lag,FALSE,#N/A,,,"A model that includes lagged values of both the dependent variable and one or more independent variables, capturing dynamic relationships over time. Used in time series analysis.","A model that includes lagged values of both the dependent variable and one or more independent variables, capturing dynamic relationships over time. Used in time series analysis.",,,,AIO:Model
AIO:GeneralizedAutoregressiveConditionalHeteroskedasticity,AIO:ModelSubset,GARCH,,Generalized Autoregressive Conditional Heteroskedasticity,FALSE,#N/A,,,"A model that incorporates lagged conditional variances, allowing for more flexibility in modeling time-varying volatility.","A model that incorporates lagged conditional variances, allowing for more flexibility in modeling time-varying volatility.",,,,AIO:Model
AIO:AutoregressiveIntegratedMovingAverage,AIO:ModelSubset,ARIMA,,Autoregressive Integrated Moving Average,FALSE,#N/A,,,"A model which combines autoregression (AR), differencing (I), and moving average (MA) components. Used for analyzing and forecasting time series data.","A model which combines autoregression (AR), differencing (I), and moving average (MA) components. Used for analyzing and forecasting time series data.",,,,AIO:Model
AIO:ModularLLM,AIO:ModelSubset,Modular Large Language Model,component skills|skill composition,Modular LLM,FALSE,0.20,,,A modular large language model that consists of multiple specialized components or skills that can be dynamically composed and recombined to solve complex tasks mimicking the modular structure of human cognition.,A modular language model that consists of multiple specialized components or skills that can be dynamically composed and recombined to solve complex tasks mimicking the modular structure of human cognition.,https://arxiv.org/abs/2302.11529v2,,,AIO:ModularLanguageModel
AIO:MultimodalLLM,AIO:ModelSubset,Multimodal Large Language Model,cross-modal grounding,Multimodal LLM,FALSE,0.34,,,A multimodal large language model that learns joint representations across different modalities like text vision and audio in an end-to-end fashion for better cross-modal understanding and generation.,A multimodal large language model that learns joint representations across different modalities like text vision and audio in an end-to-end fashion for better cross-modal understanding and generation.,https://arxiv.org/abs/2303.17580,,,AIO:MultimodalLanguageModel
AIO:MultimodalPromptbasedLanguageModel,AIO:ModelSubset,,,Multimodal Prompt-based Language Model,FALSE,#N/A,,,"A multimodal LLM which processes prompts that include multiple modalities, such as both text and images, to generate relevant responses.","A multimodal large language model which processes prompts that include multiple modalities, such as both text and images, to generate relevant responses.",https://arxiv.org/abs/2210.03094,,,AIO:MultimodalLanguageModel
AIO:MarkovChain,AIO:ModelSubset,MC|Markov Process|MP,,Markov Chain,FALSE,0.16,A Markov chain is a stochastic model describing a sequence of possible events where the probability of each event depends only on the previous event's state.,,A network that is a stochastic model describing a sequence of possible events where the probability of each event depends only on the previous event's state.,A network that is a stochastic model describing a sequence of possible events where the probability of each event depends only on the previous event's state.,https://en.wikipedia.org/wiki/Markov_chain,Layers: Probalistic Hidden,AIO:ProbabilisticHiddenLayer,AIO:Network
AIO:BidirectionalTransformerLanguageModel,AIO:ModelSubset,Bidirectional Transformer LM|BERT,,Bidirectional Transformer Language Model,FALSE,0.19,"A bidirectional transformer language model, such as BERT, uses the transformer architecture to build deep bidirectional representations by predicting masked tokens based on their context.",,A transformer language model such as BERT that uses the transformer architecture to build deep bidirectional representations by predicting masked tokens based on their context.,A transformer language model such as BERT that uses the transformer architecture to build deep bidirectional representations by predicting masked tokens based on their context.,https://arxiv.org/abs/1810.04805|https://en.wikipedia.org/wiki/BERT_(language_model)|,,,AIO:TransformerLanguageModel
AIO:TransformerLLM,AIO:ModelSubset,Transformer Large Language Model,,Transformer LLM,FALSE,0.15,"A transformer LLM is a neural network model with large training corpuses and large sets of parameters that uses the transformer architecture based on multi-head attention mechanisms, allowing it to contextualize tokens within a context window for effective language understanding and generation.",,A transformer language model with large training corpuses and sets of parameters that uses the transformer architecture based on multi-head attention mechanisms allowing it to contextualize tokens within a context window for effective language understanding and generation.,A transformer language model with large training corpuses and sets of parameters that uses the transformer architecture based on multi-head attention mechanisms allowing it to contextualize tokens within a context window for effective language understanding and generation.,https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture),,,AIO:TransformerLanguageModel
AIO:MultimodalTransformer,AIO:ModelSubset,,vision-language model|unified encoder,Multimodal Transformer,FALSE,0.39,"A multimodal transformer processes and relates information from different modalities, such as text, images, and audio. It uses a shared embedding space and attention mechanism to learn joint representations across modalities.",,A transformer network that processes and relates information from different modalities such as text images and audio using a shared embedding space and attention mechanism to learn joint representations across modalities.,A transformer network that processes and relates information from different modalities such as text images and audio using a shared embedding space and attention mechanism to learn joint representations across modalities.,,,,AIO:TransformerNetwork
AIO:Model,AIO:ModelSubset,,,Model,FALSE,0.38,"A model is an abstract representation of a complex system, generally assembled as a set of logical, mathematical, or conceptual properties to simulate or understand the system's behavior.",,An abstract representation of a complex system generally assembled as a set of logical mathematical or conceptual properties to simulate or understand the system's behavior.,An abstract representation of a complex system generally assembled as a set of logical mathematical or conceptual properties to simulate or understand the system's behavior.,https://en.wikipedia.org/wiki/Mathematical_model|,,,owl:Thing
AIO:RestrictedBoltzmannMachine,AIO:NetworkSubset,RBM,,Restricted Boltzmann Machine,FALSE,0.35,A restricted Boltzmann machine (RBM) is a generative stochastic neural network that learns the probability distribution of its input data.,,A Boltzmann machine network that learns the probability distribution of its input data.,A Boltzmann machine network that learns the probability distribution of its input data.,https://en.wikipedia.org/wiki/Restricted_Boltzmann_machine,"Layers: Backfed Input, Probabilistic Hidden",AIO:BackfedInputLayer|AIO:ProbabilisticHiddenLayer,AIO:BoltzmannMachineNetwork
AIO:NeuralTuringMachineNetwork,AIO:NetworkSubset,NTM,,Neural Turing Machine Network,FALSE,0.66,"A neural Turing machine (NTM) combines neural network pattern matching with the algorithmic power of programmable computers, using attention mechanisms to interact with external memory for tasks like copying, sorting, and associative recall.",,A deep feedforward network that combines neural network pattern matching with the algorithmic power of programmable computers.,A deep feedforward network that combines neural network pattern matching with the algorithmic power of programmable computers.,https://en.wikipedia.org/wiki/Neural_Turing_machine,"Layers: Input, Hidden, Spiking Hidden, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:SpikingHiddenLayer|AIO:OutputLayer,AIO:DeepFeedForwardNetwork
AIO:RadialBasisNetwork,AIO:NetworkSubset,RBN|Radial Basis Function Network|RBFN,,Radial Basis Network,FALSE,0.55,"Radial basis function networks use radial basis functions as activation functions, effective for pattern recognition and interpolation.",,A deep feedforward network that uses radial basis functions as activation functions for pattern recognition and interpolation.,A deep feedforward network that uses radial basis functions as activation functions for pattern recognition and interpolation.,https://en.wikipedia.org/wiki/Radial_basis_function_network,"Layers: Input, Hidden, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:DeepFeedForwardNetwork
AIO:ContrastiveLearning,AIO:NetworkSubset,,,Contrastive Learning,FALSE,0.82,"Contrastive learning is a self-supervised learning approach in which the model learns to distinguish between similar and dissimilar pairs of data samples. By maximizing the similarity between positive pairs (similar samples) and minimizing the similarity between negative pairs (dissimilar samples), the model learns to capture meaningful representations of the data. This method is particularly effective for representation learning and is widely used in tasks such as image classification, clustering, and retrieval. Contrastive learning techniques often employ loss functions such as the contrastive loss or the triplet loss to achieve these objectives.","Contrastive learning is a self-supervised learning approach in which the model learns to distinguish between similar and dissimilar pairs of data samples. By maximizing the similarity between positive pairs (similar samples) and minimizing the similarity between negative pairs (dissimilar samples), the model learns to capture meaningful representations of the data. This method is particularly effective for representation learning and is widely used in tasks such as image classification, clustering, and retrieval. Contrastive learning techniques often employ loss functions such as the contrastive loss or the triplet loss to achieve these objectives.",A deep neural network self-supervised learning approach that learns to distinguish between similar and dissimilar data samples.,A deep neural network self-supervised learning approach that learns to distinguish between similar and dissimilar data samples.,https://arxiv.org/abs/2202.14037,,,AIO:DeepNeuralNetwork
AIO:DeepConvolutionalNetwork,AIO:NetworkSubset,DCN|Convolutional Neural Network|CNN|ConvNet,,Deep Convolutional Network,FALSE,0.58,"A deep convolutional network (CNN) is an artificial neural network used to analyze visual imagery, utilizing shared-weight architecture and translation-equivariant feature maps.",,A deep neural network specialized for analyzing visual imagery using shared-weight architecture and translation-equivariant feature maps.,A deep neural network specialized for analyzing visual imagery using shared-weight architecture and translation-equivariant feature maps.,https://en.wikipedia.org/wiki/Convolutional_neural_network,"Layers: Input, Kernel, Convolutional/Pool, Hidden, Output",AIO:InputLayer|AIO:KernelLayer|AIO:ConvolutionalLayer|AIO:PoolingLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:DeepNeuralNetwork
AIO:OneshotLearning,AIO:NetworkSubset,OSL,,One-shot Learning,FALSE,#N/A,,,A deep neural network that classified objects from one or only a few examples.,A deep neural network that classified objects from one or only a few examples.,https://en.wikipedia.org/wiki/One-shot_learning,,,AIO:DeepNeuralNetwork
AIO:DeepActiveLearning,AIO:NetworkSubset,DeepAL,,Deep Active Learning,FALSE,0.33,Combining deep learning and active learning to maximize model performance gain while annotating the fewest samples possible.,,A deep neural network that combines deep learning and active learning to maximize model performance while annotating the fewest samples possible.,A deep neural network that combines deep learning and active learning to maximize model performance while annotating the fewest samples possible.,https://arxiv.org/pdf/2009.00236.pdf,,,AIO:DeepNeuralNetwork
AIO:RepresentationLearning,AIO:NetworkSubset,Feature Learning,,Representation Learning,FALSE,0.41,Discovering representations required for feature detection or classification from raw data.,Discovering representations required for feature detection or classification from raw data.,A deep neural network that discovers representations required for feature detection or classification from raw data.,A deep neural network that discovers representations required for feature detection or classification from raw data.,https://en.wikipedia.org/wiki/Feature_learning,,,AIO:DeepNeuralNetwork
AIO:ResidualNeuralNetwork,AIO:NetworkSubset,ResNN|Deep Residual Network|ResNet|DRN,,Residual Neural Network,FALSE,0.35,"A residual neural network (ResNet) employs skip connections to bypass certain layers, facilitating the learning of residual functions.",,A deep neural network that employs skip connections to bypass layers facilitating learning of residual functions.,A deep neural network that employs skip connections to bypass layers facilitating learning of residual functions.,https://en.wikipedia.org/wiki/Residual_neural_network,"Layers: Input, Weight, BN, ReLU, Weight, BN, Addition, ReLU",AIO:InputLayer|AIO:WeightedLayer|AIO:BatchNormalizationLayer|AIO:ReLULayer|AIO:AdditionLayer,AIO:DeepNeuralNetwork
AIO:MetricLearning,AIO:NetworkSubset,Distance Metric Learning,,Metric Learning,FALSE,0.47,Learning a representation function that maps objects into an embedded space.,Learning a representation function that maps objects into an embedded space.,A deep neural network that learns a representation function mapping objects into an embedded space.,A deep neural network that learns a representation function mapping objects into an embedded space.,https://paperswithcode.com/task/metric-learning,,,AIO:DeepNeuralNetwork
AIO:GeneralizedFewshotLearning,AIO:NetworkSubset,GFSL,,Generalized Few-shot Learning,FALSE,#N/A,,,"A deep neural network that learns novel classes from few samples per class, preventing catastrophic forgetting of base classes and ensuring classifier calibration.","A deep neural network that learns novel classes from few samples per class, preventing catastrophic forgetting of base classes and ensuring classifier calibration.",https://paperswithcode.com/paper/generalized-and-incremental-few-shot-learning/review/,,,AIO:DeepNeuralNetwork
AIO:ContinualLearning,AIO:NetworkSubset,Incremental Learning|Life-Long Learning,,Continual Learning,FALSE,0.48,"Learning a model for sequential tasks without forgetting knowledge from preceding tasks, with no access to old task data during new task training.","Learning a model for sequential tasks without forgetting knowledge from preceding tasks, with no access to old task data during new task training.",A deep neural network that learns sequential tasks without forgetting knowledge from preceding tasks and without access to old task data during new task training.,A deep neural network that learns sequential tasks without forgetting knowledge from preceding tasks and without access to old task data during new task training.,https://paperswithcode.com/task/continual-learning,,,AIO:DeepNeuralNetwork
AIO:GraphConvolutionalNetwork,AIO:NetworkSubset,GCN,,Graph Convolutional Network,FALSE,0.68,"A graph convolutional network (GCN) operates directly on graph structures, utilizing their structural information for tasks like node classification and graph clustering.",,A deep neural network that operates directly on graph structures utilizing structural information.,A deep neural network that operates directly on graph structures utilizing structural information.,https://arxiv.org/abs/1609.02907,"Layers: Input, Hidden, Hidden, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:DeepNeuralNetwork
AIO:ZeroshotLearning,AIO:NetworkSubset,ZSL,,Zero-shot Learning,FALSE,#N/A,,,A deep neural network that predicts classes at test time from classes not observed during training.,A deep neural network that predicts classes at test time from classes not observed during training.,https://en.wikipedia.org/wiki/Zero-shot_learning,,,AIO:DeepNeuralNetwork
AIO:MultimodalDeepLearning,AIO:NetworkSubset,,,Multimodal Deep Learning,FALSE,0.63,Creating models that process and link information using various modalities.,Creating models that process and link information using various modalities.,A deep neural network that processes and links information using various modalities.,A deep neural network that processes and links information using various modalities.,https://arxiv.org/abs/2105.11087,,,AIO:DeepNeuralNetwork
AIO:DeepFeedForwardNetwork,AIO:NetworkSubset,DFF|Multilayer Perceptoron|MLP,,Deep Feed-Forward Network,FALSE,#N/A,,,A deep neural network that processes information in one direction—from input nodes through hidden nodes to output nodes—without cycles or loops.,A deep neural network that processes information in one direction—from input nodes through hidden nodes to output nodes—without cycles or loops.,https://en.wikipedia.org/wiki/Feedforward_neural_network,"Layers: Input, Hidden, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:DeepNeuralNetwork
AIO:RecursiveNeuralNetwork,AIO:NetworkSubset,RecuNN|RvNN,,Recursive Neural Network,FALSE,0.33,A recursive neural network applies the same set of weights recursively over structured input to generate structured or scalar predictions.,,A deep neural network that recursively applies weights over structured input to generate structured or scalar predictions.,A deep neural network that recursively applies weights over structured input to generate structured or scalar predictions.,https://en.wikipedia.org/wiki/Recursive_neural_network,,,AIO:DeepNeuralNetwork
AIO:DeepTransferLearning,AIO:NetworkSubset,,,Deep Transfer Learning,FALSE,0.29,Relaxing the hypothesis that training data must be independent and identically distributed (i.i.d.) with test data to address insufficient training data.,,A deep neural network that relaxes the hypothesis that training data must be independent and identically distributed with test data to address insufficient training data.,A deep neural network that relaxes the hypothesis that training data must be independent and identically distributed with test data to address insufficient training data.,https://arxiv.org/abs/1808.01974,,,AIO:DeepNeuralNetwork
AIO:DeconvolutionalNetwork,AIO:NetworkSubset,DN,,Deconvolutional Network,FALSE,0.78,Deconvolutional networks allow unsupervised construction of hierarchical image representations for tasks such as denoising and feature extraction for object recognition.,,A deep neural network that uses deconvolution for unsupervised construction of hierarchical image representations.,A deep neural network that uses deconvolution for unsupervised construction of hierarchical image representations.,https://ieeexplore.ieee.org/document/5539957,"Layers: Input, Kernel, Convolutional/Pool, Output",AIO:InputLayer|AIO:KernelLayer|AIO:ConvolutionalLayer|AIO:PoolingLayer|AIO:OutputLayer,AIO:DeepNeuralNetwork
AIO:TransformerNetwork,AIO:NetworkSubset,,,Transformer Network,FALSE,0.63,"A transformer network utilizes attention mechanisms to weigh the significance of each part of the input data, widely used in natural language processing (NLP) and computer vision (CV).","A transformer network utilizes attention mechanisms to weigh the significance of each part of the input data, widely used in natural language processing (NLP) and computer vision (CV).",A deep neural network that utilizes attention mechanisms to weigh the significance of input data.,A deep neural network that utilizes attention mechanisms to weigh the significance of input data.,https://en.wikipedia.org/wiki/Transformer_(machine_Learning_model),,,AIO:DeepNeuralNetwork
AIO:FederatedLearning,AIO:NetworkSubset,,,Federated Learning,FALSE,0.41,Training an algorithm across multiple decentralized edge devices or servers holding local data samples without exchanging them.,Training an algorithm across multiple decentralized edge devices or servers holding local data samples without exchanging them.,A deep neural network trained across decentralized edge devices or servers holding local data samples without exchanging them.,A deep neural network trained across decentralized edge devices or servers holding local data samples without exchanging them.,https://en.wikipedia.org/wiki/Federated_learning,,,AIO:DeepNeuralNetwork
AIO:IncremenetalFewshotLearning,AIO:NetworkSubset,IFSL,,Incremenetal Few-shot Learning,FALSE,#N/A,,,"A deep neural network trained on a base set of classes and then presented with novel classes, each with few labeled examples.","A deep neural network trained on a base set of classes and then presented with novel classes, each with few labeled examples.",https://arxiv.org/abs/1810.07218,,,AIO:DeepNeuralNetwork
AIO:ExtremeLearningMachine,AIO:NetworkSubset,ELM,,Extreme Learning Machine,FALSE,0.76,"Extreme learning machines are feedforward neural networks with randomly assigned hidden node parameters that are not updated, learning output weights in a single step.",,A feedback network with randomly assigned hidden nodes that are not updated during training.,A feedback network with randomly assigned hidden nodes that are not updated during training.,https://en.wikipedia.org/wiki/Extreme_Learning_machine,"Layers: Input, Hidden, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:FeedbackNetwork
AIO:GraphConvolutionalPolicyNetwork,AIO:NetworkSubset,GPCN,,Graph Convolutional Policy Network,FALSE,0.39,"A graph convolutional policy network (GCPN) generates goal-directed graphs using a graph convolutional network and reinforcement learning, optimizing for domain-specific rewards and adversarial loss",,A graph convolutional network that generates goal-directed graphs using reinforcement learning and optimizing for rewards and adversarial loss.,A graph convolutional network that generates goal-directed graphs using reinforcement learning and optimizing for rewards and adversarial loss.,https://arxiv.org/abs/1806.02473,"Layers: Input, Hidden, Hidden, Policy, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:PolicyLayer|AIO:OutputLayer,AIO:GraphConvolutionalNetwork
AIO:GatedRecurrentUnit,AIO:NetworkSubset,GRU,,Gated Recurrent Unit,FALSE,0.43,"Gated recurrent units (GRUs) are a gating mechanism in recurrent neural networks, similar to LSTMs but with fewer parameters and no output gate.",,A long short-term memory network that is a gating mechanism in recurrent neural networks similar to LSTMs but with fewer parameters and no output gate.,A long short-term memory network that is a gating mechanism in recurrent neural networks similar to LSTMs but with fewer parameters and no output gate.,https://en.wikipedia.org/wiki/Gated_recurrent_unit,"Layers: Input, Memory Cell, Output",AIO:InputLayer|AIO:MemoryCellLayer|AIO:OutputLayer,AIO:LongShortTermMemory
AIO:node2vec,AIO:NetworkSubset,N2V,,node2vec,FALSE,#N/A,,,A machine learning designed to learn continuous feature representations for nodes in a graph by optimizing a neighborhood-preserving objective.,A machine learning task designed to learn continuous feature representations for nodes in a graph by optimizing a neighborhood-preserving objective.,https://en.wikipedia.org/wiki/Node2vec,"Layers: Input, Hidden, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:MachineLearningTask
AIO:TransferLearning,AIO:NetworkSubset,,,Transfer Learning,FALSE,0.30,Methods that reuse or transfer information from previously learned tasks to facilitate the learning of new tasks.,,A type of machine learning focused on methods that reuse or transfer information from previously learned tasks to facilitate the learning of new tasks.,A machine learning task focused on methods that reuse or transfer information from previously learned tasks to facilitate the learning of new tasks.,https://en.wikipedia.org/wiki/Transfer_learning,,,AIO:MachineLearningTask
AIO:MetaLearning,AIO:NetworkSubset,,,Meta-Learning,FALSE,#N/A,,,A machine learning that automatically learns from metadata about machine learning experiments.,A machine learning task that automatically learns from metadata about machine learning experiments.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:MachineLearningTask
AIO:word2vec,AIO:NetworkSubset,W2V,,word2vec,FALSE,#N/A,,,"A machine learning that generates distributed representations of words by training a shallow neural network model, which aims to predict the context of each word within a corpus. This algorithm captures semantic meanings of words through their contextual usage in the text.","A machine learning task that generates distributed representations of words by training a shallow neural network model, which aims to predict the context of each word within a corpus. This algorithm captures semantic meanings of words through their contextual usage in the text.",https://en.wikipedia.org/wiki/Word2vec,"Layers: Input, Hidden, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:MachineLearningTask
AIO:MultimodalLearning,AIO:NetworkSubset,,,Multimodal Learning,FALSE,0.42,"A type of deep learning that uses multiple modalities of data, such as text, audio, and images, to improve learning outcomes.","A type of deep learning that uses multiple modalities of data, such as text, audio, and images, to improve learning outcomes.",A type of machine learning that uses multiple modalities of data such as text audio and images to improve learning outcomes.,A machine learning task that uses multiple modalities of data such as text audio and images to improve learning outcomes.,https://doi.org/10.6028/NIST.SP.1270,,,AIO:MachineLearningTask
AIO:ArtificialNeuralNetwork,AIO:NetworkSubset,ANN|NN,,Artificial Neural Network,FALSE,0.58,"An artificial neural network (ANN) is based on a collection of connected units or nodes called artificial neurons, modeled after biological neurons, with connections transmitting signals processed by non-linear functions.","An artificial neural network (ANN) is based on a collection of connected units or nodes called artificial neurons, modeled after biological neurons, with connections transmitting signals processed by non-linear functions.",A network based on a collection of connected units called artificial neurons modeled after biological neurons.,A network based on a collection of connected units called artificial neurons modeled after biological neurons.,https://en.wikipedia.org/wiki/Artificial_neural_network,,,AIO:Network
AIO:UnsupervisedPretrainedNetwork,AIO:NetworkSubset,UPN,,Unsupervised Pretrained Network,FALSE,0.54,"Unsupervised pre-training initializes a discriminative neural net from one trained using an unsupervised criterion, aiding in optimization and overfitting issues.","Unsupervised pre-training initializes a discriminative neural net from one trained using an unsupervised criterion, aiding in optimization and overfitting issues.",A network that initializes a discriminative neural net from one trained using an unsupervised criterion.,A network that initializes a discriminative neural net from one trained using an unsupervised criterion.,https://metacademy.org/graphs/concepts/unsupervised_pre_training,,,AIO:Network
AIO:BayesianNetwork,AIO:NetworkSubset,,,Bayesian Network,FALSE,0.30,A probabilistic graphical model representing variables and their conditional dependencies via a directed acyclic graph (DAG).,,A network that is a probabilistic graphical model representing variables and their conditional dependencies via a directed acyclic graph.,A network that is a probabilistic graphical model representing variables and their conditional dependencies via a directed acyclic graph.,https://en.wikipedia.org/wiki/Bayesian_network,,,AIO:Network
AIO:SymmetricallyConnectedNetwork,AIO:NetworkSubset,SCN,,Symmetrically Connected Network,FALSE,0.59,"Symmetrically connected networks are a type of recurrent neural network where connections between units are symmetrical, meaning they have equal weights in both directions. This structure allows the network to maintain consistent information flow and equilibrium.","Symmetrically connected networks are a type of recurrent neural network where connections between units are symmetrical, meaning they have equal weights in both directions. This structure allows the network to maintain consistent information flow and equilibrium.",A network that is a type of recurrent neural network where connections between units are symmetrical with equal weights in both directions.,A network that is a type of recurrent neural network where connections between units are symmetrical with equal weights in both directions.,https://ieeexplore.ieee.org/document/287176,,,AIO:Network
AIO:LiquidStateMachineNetwork,AIO:NetworkSubset,LSM,,Liquid State Machine Network,FALSE,0.50,"A liquid state machine (LSM) is a type of reservoir computer using a spiking neural network, with recurrently connected nodes turning time-varying input into spatio-temporal activation patterns.",,A network that is a type of reservoir computer turning time-varying input into spatio-temporal activation patterns.,A network that is a type of reservoir computer turning time-varying input into spatio-temporal activation patterns.,https://en.wikipedia.org/wiki/Liquid_state_machine,"Layers: Input, Spiking Hidden, Output",AIO:InputLayer|AIO:SpikingHiddenLayer|AIO:OutputLayer,AIO:Network
AIO:KohonenNetwork,AIO:NetworkSubset,KN|Self-Organizing Map|SOM|Self-Organizing Feature Map|SOFM,,Kohonen Network,FALSE,0.40,"A self-organizing map (SOM) or Kohonen network is an unsupervised machine learning technique producing a low-dimensional representation of high-dimensional data, preserving topological structure.",,A network that is an unsupervised technique producing a low-dimensional representation of high-dimensional data preserving topological structure.,A network that is an unsupervised technique producing a low-dimensional representation of high-dimensional data preserving topological structure.,https://en.wikipedia.org/wiki/Self-organizing_map,"Layers: Input, Hidden",AIO:InputLayer|AIO:HiddenLayer,AIO:Network
AIO:RecurrentNeuralNetwork,AIO:NetworkSubset,RecNN|Recurrent Network|RN,,Recurrent Neural Network,FALSE,0.35,"A recurrent neural network (RNN) has connections forming a directed graph along a temporal sequence, enabling dynamic temporal behavior.",,A deep neural network with connections forming a directed graph along a temporal sequence enabling dynamic behavior.,A network with connections forming a directed graph along a temporal sequence enabling dynamic behavior.,,,,AIO:Network
AIO:SupportVectorMachine,AIO:NetworkSubset,SVM|Supper Vector Network|SVN,,Support Vector Machine,FALSE,0.45,"Support vector machines (SVMs) are supervised learning models for classification and regression analysis, mapping training examples to points in space to maximize the gap between categories.",,A network with supervised learning models for classification and regression that maps training examples to points in space maximizing the gap between categories.,A network with supervised learning models for classification and regression that maps training examples to points in space maximizing the gap between categories.,https://en.wikipedia.org/wiki/Support-vector_machine,"Layers: Input, Hidden, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:Network
AIO:node2vecCBOW,AIO:NetworkSubset,N2V-CBOW,CBOW,node2vec-CBOW,FALSE,#N/A,,,"A node2vec that predicts the current node from a window of surrounding context nodes, with the order of context nodes not influencing prediction.","A node2vec that predicts the current node from a window of surrounding context nodes, with the order of context nodes not influencing prediction.",https://en.wikipedia.org/wiki/Node2vec,"Layers: Input, Hidden, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:node2vec
AIO:node2vecSkipGram,AIO:NetworkSubset,N2V-SkipGram,SkipGram,node2vec-SkipGram,FALSE,#N/A,,,"A node2vec that uses the current node to predict the surrounding window of context nodes, weighing nearby context nodes more heavily than distant ones.","A node2vec that uses the current node to predict the surrounding window of context nodes, weighing nearby context nodes more heavily than distant ones.",https://en.wikipedia.org/wiki/Node2vec,"Layers: Input, Hidden, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:node2vec
AIO:EchoStateNetwork,AIO:NetworkSubset,ESN,,Echo State Network,FALSE,0.53,"An echo state network (ESN) is a type of reservoir computer with a recurrent neural network and a sparsely connected hidden layer, learning output neuron weights to produce temporal patterns.",,A recurrent neural network with a recurrent hidden layer and sparsely connected hidden neurons that learns output weights to produce temporal patterns.,A recurrent neural network with a recurrent hidden layer and sparsely connected hidden neurons that learns output weights to produce temporal patterns.,https://en.wikipedia.org/wiki/Echo_state_network,"Layers: Input, Recurrent, Output",AIO:InputLayer|AIO:RecurrentLayer|AIO:OutputLayer,AIO:RecurrentNeuralNetwork
AIO:LongShortTermMemory,AIO:NetworkSubset,LSTM,,Long Short Term Memory,FALSE,0.77,"Long short-term memory (LSTM) networks are artificial recurrent neural networks with feedback connections, processing entire sequences of data for tasks like handwriting and speech recognition.",,A recurrent neural network with feedback connections that processes entire sequences of data.,A recurrent neural network with feedback connections that processes entire sequences of data.,https://en.wikipedia.org/wiki/Long_short-term_memory,"Layers: Input, Memory Cell, Output",AIO:InputLayer|AIO:MemoryCellLayer|AIO:OutputLayer,AIO:RecurrentNeuralNetwork
AIO:SparseLearning,AIO:NetworkSubset,Sparse dictionary Learning|Sparse coding,,Sparse Learning,FALSE,0.39,Finding sparse representations of input data as a linear combination of basic elements and identifying those elements.,,A representation learning network that finds sparse representations of input data as a linear combination of basic elements and identifies those elements.,A representation learning network that finds sparse representations of input data as a linear combination of basic elements and identifies those elements.,https://en.wikipedia.org/wiki/Sparse_dictionary_learning,,,AIO:RepresentationLearning
AIO:HopfieldNetwork,AIO:NetworkSubset,HN|Ising model of a neural network|Ising–Lenz–Little model,,Hopfield Network,FALSE,0.64,"A Hopfield network is a type of recurrent artificial neural network that serves as a content-addressable (""associative"") memory system. It uses binary threshold nodes or continuous variables to store and recall memory patterns, providing a model for understanding human memory.",,A symmetrically connected network that is a type of recurrent artificial neural network serving as a content-addressable memory system.,A symmetrically connected network that is a type of recurrent artificial neural network serving as a content-addressable memory system.,https://en.wikipedia.org/wiki/Hopfield_network,Layers: Backfed input,AIO:BackfedInputLayer,AIO:SymmetricallyConnectedNetwork
AIO:BoltzmannMachineNetwork,AIO:NetworkSubset,BM|stochastic Hopfield network with hidden units|Sherrington–Kirkpatrick model with external field|stochastic Ising-Lenz-Little model,,Boltzmann Machine Network,FALSE,0.57,"A Boltzmann machine is a type of stochastic recurrent neural network and Markov random field, translated from statistical physics for use in cognitive science.",,A symmetrically connected network that is a type of stochastic recurrent neural network and Markov random field.,A symmetrically connected network that is a type of stochastic recurrent neural network and Markov random field.,https://en.wikipedia.org/wiki/Boltzmann_machine,"Layers: Backfed Input, Probabilistic Hidden",AIO:BackfedInputLayer|AIO:ProbabilisticHiddenLayer,AIO:SymmetricallyConnectedNetwork
AIO:word2vecSkipGram,AIO:NetworkSubset,W2V-SkipGram,SkipGram,word2vec-SkipGram,FALSE,#N/A,,,"A word2vec that predicts surrounding context words from the current word, giving more weight to nearby context words than distant ones.","A word2vec that predicts surrounding context words from the current word, giving more weight to nearby context words than distant ones.",https://en.wikipedia.org/wiki/Word2vec,"Layers: Input, Hidden, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:word2vec
AIO:word2vecCBOW,AIO:NetworkSubset,W2V-CBOW,CBOW,word2vec-CBOW,FALSE,#N/A,,,"A word2vec that predicts the current word from a window of surrounding context words, ignoring the order of context words.","A word2vec that predicts the current word from a window of surrounding context words, ignoring the order of context words.",https://en.wikipedia.org/wiki/Word2vec,"Layers: Input, Hidden, Output",AIO:InputLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:word2vec
AIO:DeepNeuralNetwork,AIO:NetworkSubset,DNN,,Deep Neural Network,FALSE,0.81,"A deep neural network (DNN) is a type of artificial neural network (ANN) characterized by multiple hidden layers between the input and output layers. Each layer consists of interconnected neurons that process and transmit information. DNNs can model complex patterns and representations in data through their hierarchical structure, where each layer extracts increasingly abstract features from the input. DNNs are widely used in various applications, including image and speech recognition, natural language processing, and more, due to their ability to learn and generalize from large amounts of data.","A deep neural network (DNN) is a type of artificial neural network (ANN) characterized by multiple hidden layers between the input and output layers. Each layer consists of interconnected neurons that process and transmit information. DNNs can model complex patterns and representations in data through their hierarchical structure, where each layer extracts increasingly abstract features from the input. DNNs are widely used in various applications, including image and speech recognition, natural language processing, and more, due to their ability to learn and generalize from large amounts of data.",An artificial neural network characterized by multiple hidden layers between the input and output layers.,An artificial neural network characterized by multiple hidden layers between the input and output layers.,,,,AIO:ArtificialNeuralNetwork
AIO:FeedbackNetwork,AIO:NetworkSubset,FBN,,Feedback Network,FALSE,0.35,A feedback network iteratively refines its representations based on feedback from previous iterations' outputs.,,An artificial neural network that refines its representations iteratively based on feedback from previous outputs.,An artificial neural network that refines its representations iteratively based on feedback from previous outputs.,,"Layers: Input, Hidden, Output, Hidden",AIO:InputLayer|AIO:HiddenLayer|AIO:OutputLayer,AIO:ArtificialNeuralNetwork
AIO:Perceptron,AIO:NetworkSubset,Single Layer Perceptron|SLP|Feed-Forward Network|FFN,,Perceptron,FALSE,0.71,"A perceptron is a supervised learning algorithm for binary classification, deciding if an input belongs to a class using a linear predictor function that combines weights with the feature vector.",,An artificial neural network with a supervised learning algorithm for binary classification using a linear predictor function.,An artificial neural network with a supervised learning algorithm for binary classification using a linear predictor function.,,"Layers: Input, Output",AIO:InputLayer|AIO:OutputLayer,AIO:ArtificialNeuralNetwork
AIO:VariationalAutoEncoder,AIO:NetworkSubset,VAE,,Variational Auto Encoder,FALSE,0.84,"A variational autoencoder (VAE) is a type of artificial neural network used for unsupervised learning. It consists of an encoder, which maps input data to a latent space, and a decoder, which reconstructs the input data from the latent space. Unlike traditional autoencoders, VAEs impose a probabilistic structure on the latent space, enabling them to generate new data samples by sampling from the learned latent distribution. This probabilistic approach allows VAEs to learn smooth and meaningful latent representations, making them useful for tasks such as data generation, anomaly detection, and semi-supervised learning.",,An autoencoder network that imposes a probabilistic structure on the latent space for unsupervised learning.,An autoencoder network that imposes a probabilistic structure on the latent space for unsupervised learning.,,"Layers: Input, Probabilistic Hidden, Matched Output-Input",AIO:InputLayer|AIO:ProbabilisticHiddenLayer|AIO:MatchedInputOutputLayer,AIO:AutoEncoderNetwork
AIO:DeepConvolutionalInverseGraphicsNetwork,AIO:NetworkSubset,DCIGN,,Deep Convolutional Inverse Graphics Network,FALSE,0.59,A deep convolutional inverse graphics network (DC-IGN) learns interpretable image representations disentangled for transformations like out-of-plane rotations and lighting variations. It consists of convolution and de-convolution layers and is trained using the stochastic gradient variational Bayes (SGVB) algorithm.,,An autoencoder network that learns interpretable disentangled image representations through convolution and de-convolution layers trained with the stochastic gradient variational Bayes algorithm.,An autoencoder network that learns interpretable disentangled image representations through convolution and de-convolution layers trained with the stochastic gradient variational Bayes algorithm.,,"Layers: Input, Kernel, Convolutional/Pool, Probabilistic Hidden, Convolutional/Pool, Kernel, Output",AIO:InputLayer|AIO:KernelLayer|AIO:ConvolutionalLayer|AIO:PoolingLayer|AIO:ProbabilisticHiddenLayer|AIO:OutputLayer,AIO:AutoEncoderNetwork
AIO:DenoisingAutoEncoder,AIO:NetworkSubset,DAE|Denoising Autoencoder,,Denoising Auto Encoder,FALSE,0.54,"Denoising autoencoders (DAEs) are neural networks trained to reconstruct the original undistorted input from a partially corrupted input, aiming to clean or denoise the corrupted input.",,An autoencoder network trained to reconstruct the original undistorted input from a partially corrupted input.,An autoencoder network trained to reconstruct the original undistorted input from a partially corrupted input.,https://doi.org/10.1145/1390156.1390294,"Layers: Noisy Input, Hidden, Matched Output-Input",AIO:NoisyInputLayer|AIO:HiddenLayer|AIO:MatchedInputOutputLayer,AIO:AutoEncoderNetwork
AIO:SparseAutoEncoder,AIO:NetworkSubset,SAE|Sparse AE|Sparse Autoencoder,,Sparse Auto Encoder,FALSE,0.66,"Sparse autoencoders have more hidden units than inputs but constrain only a few hidden units to be active at once, forcing the model to capture unique statistical features of the training data.",,An autoencoder network with more hidden units than inputs that constrains only a few hidden units to be active at once.,An autoencoder network with more hidden units than inputs that constrains only a few hidden units to be active at once.,,"Layers: Input, Hidden, Matched Output-Input",AIO:InputLayer|AIO:HiddenLayer|AIO:MatchedInputOutputLayer,AIO:AutoEncoderNetwork
AIO:DeepBeliefNetwork,AIO:NetworkSubset,DBN,,Deep Belief Network,FALSE,0.57,"A deep belief network (DBN) is a generative graphical model composed of multiple layers of latent variables, learning to probabilistically reconstruct inputs and perform classification.",,An unsupervised pretrained network composed of multiple layers of latent variables that learns to probabilistically reconstruct inputs and perform classification.,An unsupervised pretrained network composed of multiple layers of latent variables that learns to probabilistically reconstruct inputs and perform classification.,https://en.wikipedia.org/wiki/Deep_belief_network,"Layers: Backfed Input, Probabilistic Hidden, Hidden, Matched Output-Input",AIO:BackfedInputLayer|AIO:ProbabilisticHiddenLayer|AIO:HiddenLayer|AIO:MatchedInputOutputLayer,AIO:UnsupervisedPretrainedNetwork
AIO:GenerativeAdversarialNetwork,AIO:NetworkSubset,GAN,,Generative Adversarial Network,FALSE,0.32,A generative adversarial network (GAN) is a machine learning framework where two neural networks contest in a game to generate new data with the same statistics as the training set.,,An unsupervised pretrained network framework where two neural networks contest in a game to generate new data with the same statistics as the training set.,An unsupervised pretrained network framework where two neural networks contest in a game to generate new data with the same statistics as the training set.,https://en.wikipedia.org/wiki/Generative_adversarial_network,"Layers: Backfed Input, Hidden, Matched Output-Input, Hidden, Matched Output-Input",AIO:BackfedInputLayer|AIO:HiddenLayer|AIO:MatchedInputOutputLayer,AIO:UnsupervisedPretrainedNetwork
AIO:AutoEncoderNetwork,AIO:NetworkSubset,AE,,Auto Encoder Network,FALSE,0.48,"An autoencoder is an artificial neural network used for learning efficient codings of unlabeled data, training the network to ignore insignificant data and regenerate input from encoding.",,An unsupervised pretrained network that learns efficient codings of unlabeled data by training to ignore insignificant data and regenerate input from encoding.,An unsupervised pretrained network that learns efficient codings of unlabeled data by training to ignore insignificant data and regenerate input from encoding.,https://en.wikipedia.org/wiki/Autoencoder,"Layers: Input, Hidden, Matched Output-Input",AIO:InputLayer|AIO:HiddenLayer|AIO:MatchedInputOutputLayer,AIO:UnsupervisedPretrainedNetwork
AIO:FeatureExtraction,AIO:PreprocessingSubset,Attribute Extraction|Feature Isolation,Syntactic information|Semantic embeddings,Feature Extraction,FALSE,0.07,"The process of transforming raw data into a set of measurable characteristics that can be used as input for machine learning algorithms, enhancing the ability to make accurate predictions.",,The process of transforming raw data into a set of measurable characteristics that can be used as input for machine learning algorithms enhancing the ability to make accurate predictions.,"A data enhancement that transforms raw data into a set of measurable characteristics that can be used as input for machine learning algorithms, enhancing the ability to make accurate predictions.",,,,AIO:DataEnhancement
AIO:DataAugmentation,AIO:PreprocessingSubset,Data Expansion|Data Enrichment,Paraphrasing|Synonym replacement,Data Augmentation,FALSE,0.24,"A technique used to increase the diversity and quantity of training data by applying various transformations such as rotation, scaling, flipping, and cropping to existing data samples, enhancing the robustness and performance of machine learning models.",,A technique used to increase the diversity and quantity of training data by applying various transformations such as rotation scaling flipping and cropping to existing data samples enhancing the robustness and performance of machine learning models.,A data enhancement used to increase the diversity and quantity of training data by applying various transformations such as rotation scaling flipping and cropping to existing data samples enhancing the robustness and performance of machine learning models.,,,,AIO:DataEnhancement
AIO:Tokenization,AIO:PreprocessingSubset,Lexical Analysis|Text Segmentation,,Tokenization,FALSE,0.21,"The process of converting a sequence of text into smaller, meaningful units called tokens, typically words or subwords, for the purpose of analysis or processing by language models.",,The process of converting a sequence of text into smaller meaningful units called tokens typically words or subwords for the purpose of analysis or processing by language models.,A data preparation that converts a sequence of text into smaller meaningful units called tokens typically words or subwords for the purpose of analysis or processing by language models.,,,,AIO:DataPreparation
AIO:SubwordSegmentation,AIO:PreprocessingSubset,Fragmentation|Part-word Division,Byte Pair Encoding|SentencePiece,Subword Segmentation,FALSE,0.12,"The process of dividing text into subword units, which are smaller than words but larger than individual characters, to improve the efficiency and effectiveness of natural language processing models by capturing meaningful subunits of words.",,The process of dividing text into subword units which are smaller than words but larger than individual characters to improve the efficiency and effectiveness of natural language processing models by capturing meaningful subunits of words.,A data preparation that divides text into subword units which are smaller than words but larger than individual characters to improve the efficiency and effectiveness of natural language processing models by capturing meaningful subunits of words.,,,,AIO:DataPreparation
AIO:VocabularyReduction,AIO:PreprocessingSubset,Vocabulary Condensation|Lexical Simplification|Lexicon Pruning,,Vocabulary Reduction,FALSE,0.11,"The technique of limiting the number of unique tokens in a language model’s vocabulary by merging or eliminating less frequent tokens, thereby optimizing computational efficiency and resource usage.",,The technique of limiting the number of unique tokens in a language model's vocabulary by merging or eliminating less frequent tokens thereby optimizing computational efficiency and resource usage.,A data preparation that limits the number of unique tokens in a language model's vocabulary by merging or eliminating less frequent tokens thereby optimizing computational efficiency and resource usage.,,,,AIO:DataPreparation
AIO:Cleaning,AIO:PreprocessingSubset,Data Cleansing|Standardization,Data cleaning|Text normalization,Cleaning,FALSE,0.17,"The process of removing noise, inconsistencies, and irrelevant information from data to enhance its quality and prepare it for analysis or further processing.",,The process of removing noise inconsistencies and irrelevant information from data to enhance its quality and prepare it for analysis or further processing.,A data preparation that removes noise inconsistencies and irrelevant information from data to enhance its quality and prepare it for analysis or further processing.,,,,AIO:DataPreparation
AIO:Normalization,AIO:PreprocessingSubset,,,Normalization,FALSE,#N/A,"The technique of transforming data into a standard format or scale, typically to reduce redundancy and improve consistency, often involving the adjustment of values measured on different scales to a common scale.",,The technique of transforming data into a standard format or scale typically to reduce redundancy and improve consistency often involving the adjustment of values measured on different scales to a common scale.,A data preparation that transforms data into a standard format or scale typically to reduce redundancy and improve consistency often involving the adjustment of values measured on different scales to a common scale.,,,,AIO:DataPreparation
AIO:DataPreparation,AIO:PreprocessingSubset,Data Curation|Data Processing|Data Assembly,,Data Preparation,FALSE,0.23,"The process of cleaning, transforming, and organizing raw data into a suitable format for analysis and modeling, ensuring the quality and relevance of the data for machine learning tasks.",,The process of cleaning transforming and organizing raw data into a suitable format for analysis and modeling ensuring the quality and relevance of the data for machine learning tasks.,"A preprocessing that cleans, transforms and organizes raw data into a suitable format for analysis and modeling, ensuring the quality and relevance of the data for machine learning tasks.",,,,AIO:Preprocessing
AIO:Distillation,AIO:PreprocessingSubset,Refining|Purification,Knowledge compression|Teacher-student model,Distillation,FALSE,0.04,"The process of training a smaller model to replicate the behavior of a larger model, aiming to compress the knowledge into a more compact form without significant loss of performance.",,The process of training a smaller model to replicate the behavior of a larger model aiming to compress the knowledge into a more compact form without significant loss of performance.,A preprocessing that trains a smaller model to replicate the behavior of a larger model aiming to compress the knowledge into a more compact form without significant loss of performance.,https://doi.org/10.48550/arXiv.2105.13093,,,AIO:TrainingStrategy
AIO:DataEnhancement,AIO:PreprocessingSubset,AIO:PreprocessingSubset,,DataEnhancement,FALSE,0.38,"Techniques used to improve the quality, diversity, and volume of data available for training machine learning models, such as data augmentation, synthesis, and enrichment, to enhance model robustness and accuracy.",,Techniques used to improve the quality diversity and volume of data available for training machine learning models such as data augmentation synthesis and enrichment to enhance model robustness and accuracy.,"A preprocessing used to improve the quality diversity and volume of data available for training machine learning models, such as data augmentation synthesis and enrichment to enhance model robustness and accuracy.",,,,AIO:Preprocessing
AIO:TrainingStrategy,AIO:TrainingStrategySubset,Learning Techniques|Instructional Methods,,TrainingStrategy,FALSE,#N/A,"The methodologies and approaches used to train machine learning models, including techniques such as supervised learning, unsupervised learning, reinforcement learning, and transfer learning, aimed at optimizing model performance.",,The methodologies and approaches used to train machine learning models including techniques such as supervised learning unsupervised learning reinforcement learning and transfer learning aimed at optimizing model performance.,A preprocessing used to train machine learning models including techniques such as supervised learning unsupervised learning reinforcement learning and transfer learning aimed at optimizing model performance.,,,,owl:Thing
AIO:CurriculumLearning,AIO:TrainingStrategySubset,Sequential Learning|Structured Learning,Sequential learning|Complexity grading,Curriculum Learning,FALSE,0.13,"A training strategy in machine learning where models are trained on data in a meaningful order, starting with simpler examples and gradually increasing the complexity, to improve learning efficiency and model performance.",,A training strategy in machine learning where models are trained on data in a meaningful order starting with simpler examples and gradually increasing the complexity to improve learning efficiency and model performance.,A training strategy in machine learning where models are trained on data in a meaningful order starting with simpler examples and gradually increasing the complexity to improve learning efficiency and model performance.,,,,AIO:TrainingStrategy
AIO:KnowledgeTransfer,AIO:TrainingStrategySubset,Inductive Transfer,Pretrained models|Adaptation,Knowledge Transfer,FALSE,0.32,"The process by which knowledge is passed from one entity, such as a person, organization, or system, to another, facilitating learning and adaptation in the receiving entity through various methods such as teaching, training, or data exchange.",,The process by which knowledge is passed from one entity such as a person organization or system to another facilitating learning and adaptation in the receiving entity through various methods such as teaching training or data exchange.,A training strategy in which knowledge is passed from one entity such as a person organization or system to another facilitating learning and adaptation in the receiving entity through various methods such as teaching training or data exchange.,https://doi.org/10.1016/j.knosys.2015.01.010|,,,AIO:TrainingStrategy
AIO:Preprocessing,AIO:PreprocessingSubset,,,Preprocessing,FALSE,0.26,"A process applied to raw data before it is used in a machine learning model, including tasks such as normalization, scaling, encoding, and transformation, to ensure the data is in an appropriate format and quality for analysis.",,The series of steps applied to raw data before it is used in a machine learning model including tasks such as normalization scaling encoding and transformation to ensure the data is in an appropriate format and quality for analysis.,"A process applied to raw data before it is used in a machine learning model, including tasks such as normalization, scaling, encoding, and transformation, to ensure the data is in an appropriate format and quality for analysis.",https://doi.org/10.1109/ICDE.2019.00245,,,owl:Thing