Entropy-Based Logic Explanations of Neural Networks


  • Pietro Barbiero University of Cambridge
  • Gabriele Ciravegna University of Florence University of Siena Université Côte d'Azur
  • Francesco Giannini University of Siena
  • Pietro Lió University of Cambridge
  • Marco Gori University of Siena Université Côte d'Azur
  • Stefano Melacci University of Siena




Machine Learning (ML), Humans And AI (HAI)


Explainable artificial intelligence has rapidly emerged since lawmakers have started requiring interpretable models for safety-critical domains. Concept-based neural networks have arisen as explainable-by-design methods as they leverage human-understandable symbols (i.e. concepts) to predict class memberships. However, most of these approaches focus on the identification of the most relevant concepts but do not provide concise, formal explanations of how such concepts are leveraged by the classifier to make predictions. In this paper, we propose a novel end-to-end differentiable approach enabling the extraction of logic explanations from neural networks using the formalism of First-Order Logic. The method relies on an entropy-based criterion which automatically identifies the most relevant concepts. We consider four different case studies to demonstrate that: (i) this entropy-based criterion enables the distillation of concise logic explanations in safety-critical domains from clinical data to computer vision; (ii) the proposed approach outperforms state-of-the-art white-box models in terms of classification accuracy.




How to Cite

Barbiero, P., Ciravegna, G., Giannini, F., Lió, P., Gori, M., & Melacci, S. (2022). Entropy-Based Logic Explanations of Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 36(6), 6046-6054. https://doi.org/10.1609/aaai.v36i6.20551



AAAI Technical Track on Machine Learning I