Explaining AI decisions using efficient methods for learning sparse Boolean formulae

DOI10.1007/s10817-018-9499-8zbMath1468.68149OpenAlexW2903500849MaRDI QIDQ2331079

Yanyan Li

Publication date: 25 October 2019

Published in: Journal of Automated Reasoning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10817-018-9499-8

zbMATH Keywords

formal methodsmachine learningsparse learningexplainable AIinterpretable AIBoolean formula learning

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) General topics in artificial intelligence (68T01)

Related Items (2)

Explaining AI decisions using efficient methods for learning sparse Boolean formulae ⋮ Explainable Deep Learning: A Field Guide for the Uninitiated

Uses Software

• MNIST

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Theory revision with queries: Horn, read-once, and parity formulas
• A theory of formal synthesis via inductive learning
• Counterexample-guided quantifier instantiation for synthesis in SMT
• A general lower bound on the number of examples needed for learning
• When won't membership queries help?
• Ranking function synthesis for bit-vector relations
• Explaining AI decisions using efficient methods for learning sparse Boolean formulae
• On PAC learning algorithms for rich Boolean function classes
• Constructing invariants for hybrid systems
• Sigma*
• Automatic invariant generation for hybrid systems using ideal fixed points
• The coupon-collector problem revisited — a survey of engineering problems and computational methods
• Computational limitations on learning from examples
• Cryptographic limitations on learning Boolean formulae and finite automata
• Learning Boolean formulas
• Planning Algorithms

This page was built for publication: Explaining AI decisions using efficient methods for learning sparse Boolean formulae