Towards formal XAI: formally approximate minimal explanations of neural networks

DOI10.1007/978-3-031-30823-9_10MaRDI QIDQ6535352

Guy Katz, Shahaf Bassan

Publication date: 13 December 2023

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cites Work

• On the minimum hitting set of bundles problem
• A theory of diagnosis from first principles
• A SAT-based approach to learn explainable decision sets
• SAT-based rigorous explanations for decision lists
• Reluplex: an efficient SMT solver for verifying deep neural networks
• An abstraction-based framework for neural network verification
• An SMT-based approach for verifying binarized neural networks
• Redundancy in logic. I: CNF propositional formulae
• The Minimal Hitting Set Generation Problem: Algorithms and Computation
• On Tackling Explanation Redundancy in Decision Trees
• The Computational Complexity of Understanding Binary Classifier Decisions
• Global optimization of objective functions represented by ReLU networks
• Reluplex: a calculus for reasoning about deep neural networks
• Neural Network Verification Using Residual Reasoning
• On computing probabilistic abductive explanations
• Run-time optimization for learned controllers through quantitative games
• Efficient neural network analysis with sum-of-infeasibilities

Related Items (5)

Scrutinizing XAI using linear ground-truth data with suppressor variables ⋮ The explanation game: a formal framework for interpretable machine learning ⋮ On the failings of Shapley values for explainability ⋮ Verifying the generalization of deep learning to out-of-distribution domains ⋮ Explaining AI decisions using efficient methods for learning sparse Boolean formulae

Recommendations

• Title not available (Why is that?) 👍 👎
• Explicative deep learning with probabilistic formal concepts in a natural language processing task 👍 👎
• The quest of parsimonious XAI: a human-agent architecture for explanation formulation 👍 👎
• Explaining AI decisions using efficient methods for learning sparse Boolean formulae 👍 👎
• A formal proof of the expressiveness of deep learning 👍 👎
• A formal proof of the expressiveness of deep learning 👍 👎
• The explanation game: a formal framework for interpretable machine learning 👍 👎

This page was built for publication: Towards formal XAI: formally approximate minimal explanations of neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6535352)