Entropy-based Logic Explanations of Neural Networks - Laboratoire d'Informatique, Signaux et Systèmes de Sophia-Antipolis Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Entropy-based Logic Explanations of Neural Networks

Résumé

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 and matches black box performances.
Fichier principal
Vignette du fichier
elens_aaai.pdf (1.08 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03507746 , version 1 (03-01-2022)

Identifiants

  • HAL Id : hal-03507746 , version 1

Citer

Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini, Pietro Lió, Marco Gori, et al.. Entropy-based Logic Explanations of Neural Networks. AAAI 2022 - 36th AAAI conference on artificial intelligence, AAAI, Feb 2022, Vancouver, United States. ⟨hal-03507746⟩
53 Consultations
98 Téléchargements

Partager

Gmail Facebook X LinkedIn More