Certified logic-based explainable AI -- the case of monotonic classifiers

DOI10.1007/978-3-031-38828-6_4zbMATH Open1541.68219MaRDI QIDQ6535329FDOQ6535329

Authors: Aurélie Hurault, Joao Marques-Silva 

Publication date: 12 December 2023

Recommendations

• Towards formal XAI: formally approximate minimal explanations of neural networks
• A unified logical framework for explanations in classifier systems
• A logic for binary classifiers and their explanation
• Non-monotonic explanation functions
• Feature necessity \& relevancy in ML classifier explanations

zbMATH Keywords

certificationformal explainability

Mathematics Subject Classification ID

Specification and verification (program logics, model checking, etc.) (68Q60) Formalization of mathematics in connection with theorem provers (68V20) General topics in artificial intelligence (68T01)

Cites Work

• Minimal sets on propositional formulae. Problems and reductions
• A theory of diagnosis from first principles
• Formally verifying the solution to the Boolean Pythagorean triples problem
• Explanation in artificial intelligence: insights from the social sciences
• Handbook of satisfiability. In 2 parts

Cited In (1)

• On the failings of Shapley values for explainability

This page was built for publication: Certified logic-based explainable AI -- the case of monotonic classifiers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6535329)