Non-monotonic explanation functions

DOI10.1007/978-3-030-86772-0_2MaRDI QIDQ2145997zbMATH OpenOpenAlexFDO

Authors Leila Amgoud

Publication date 15 June 2022

Full work available at URL https://doi.org/10.1007/978-3-030-86772-0_2

zbMATH Keywords

classificationargumentationexplainability

Mathematics Subject Classification ID

Reasoning under uncertainty in the context of artificial intelligence (68T37)

Recommendations

• A new class of explanations for classifiers with non-binary features
• Foundations of fine-grained explainability
• Considerations when learning additive explanations for black-box models
• Feature necessity \& relevancy in ML classifier explanations
• How to explain individual classification decisions

Cites work

• Explanation in artificial intelligence: insights from the social sciences
• On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and \(n\)-person games
• On the reasons behind decisions

Cited in

(5)

• A new class of explanations for classifiers with non-binary features
• On the failings of Shapley values for explainability
• Certified logic-based explainable AI -- the case of monotonic classifiers
• On computing probabilistic abductive explanations
• Explaining black-box classifiers: properties and functions

This page was built for publication: Non-monotonic explanation functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2145997)