English

Probably Approximately Correct Explanations of Machine Learning Models via Syntax-Guided Synthesis

Artificial Intelligence 2020-09-21 v1

Abstract

We propose a novel approach to understanding the decision making of complex machine learning models (e.g., deep neural networks) using a combination of probably approximately correct learning (PAC) and a logic inference methodology called syntax-guided synthesis (SyGuS). We prove that our framework produces explanations that with a high probability make only few errors and show empirically that it is effective in generating small, human-interpretable explanations.

Keywords

Cite

@article{arxiv.2009.08770,
  title  = {Probably Approximately Correct Explanations of Machine Learning Models via Syntax-Guided Synthesis},
  author = {Daniel Neider and Bishwamittra Ghosh},
  journal= {arXiv preprint arXiv:2009.08770},
  year   = {2020}
}
R2 v1 2026-06-23T18:38:15.488Z