Extracting Formulae in Many-Valued Logic from Deep Neural Networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Yani, Bölcskei, Helmut
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915183451963392
author Zhang, Yani
Bölcskei, Helmut
author_facet Zhang, Yani
Bölcskei, Helmut
contents We propose a new perspective on deep ReLU networks, namely as circuit counterparts of Lukasiewicz infinite-valued logic -- a many-valued (MV) generalization of Boolean logic. An algorithm for extracting formulae in MV logic from deep ReLU networks is presented. As the algorithm applies to networks with general, in particular also real-valued, weights, it can be used to extract logical formulae from deep ReLU networks trained on data.
format Preprint
id arxiv_https___arxiv_org_abs_2401_12113
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Extracting Formulae in Many-Valued Logic from Deep Neural Networks
Zhang, Yani
Bölcskei, Helmut
Machine Learning
Artificial Intelligence
Logic in Computer Science
We propose a new perspective on deep ReLU networks, namely as circuit counterparts of Lukasiewicz infinite-valued logic -- a many-valued (MV) generalization of Boolean logic. An algorithm for extracting formulae in MV logic from deep ReLU networks is presented. As the algorithm applies to networks with general, in particular also real-valued, weights, it can be used to extract logical formulae from deep ReLU networks trained on data.
title Extracting Formulae in Many-Valued Logic from Deep Neural Networks
topic Machine Learning
Artificial Intelligence
Logic in Computer Science
url https://arxiv.org/abs/2401.12113