Editable machine learning models? A rule-based framework for user studies of explainability

DOI10.1007/S11634-020-00419-2MaRDI QIDQ2022486zbMATH OpenOpenAlexFDO

Authors Stanislav Vojíř, Tomáš Kliegr

Publication date 29 April 2021

Published in Advances in Data Analysis and Classification. ADAC (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s11634-020-00419-2

zbMATH Keywords

cognitive computingcrowdsourcingexplainable artificial intelligencelegal compliancerule learninguser experiment

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Knowledge representation (68T30)

Recommendations

• On cognitive preferences and the plausibility of rule-based models
• Definitions, methods, and applications in interpretable machine learning
• A Bayesian framework for learning rule sets for interpretable classification
• Interactive machine learning: Letting users build classifiers
• The interpretability of rule-based modeling approach and its development

Cites work

• A Bayesian framework for learning rule sets for interpretable classification
• Do we need hundreds of classifiers to solve real world classification problems?
• Explanation in artificial intelligence: insights from the social sciences
• Foundations of Rule Learning
• On cognitive preferences and the plausibility of rule-based models
• The GUHA method of automatic hypotheses determination
• Ultra-strong machine learning: comprehensibility of programs learned with ILP

Cited in

(3)

• Disjunctive Rule Lists
• On the efficient implementation of classification rule learning
• RGA: a unified measure of predictive accuracy

Describes a project that uses

Uses Software

• RuleML
• Psychophysics Toolbox
• PyGaze
• DeepRED

This page was built for publication: Editable machine learning models? A rule-based framework for user studies of explainability

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2022486)