Neural networks as fuzzy logic formulas

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Heiman, Damian, Kuusisto, Antti, Turunen, Esko
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910190694039552
author Heiman, Damian
Kuusisto, Antti
Turunen, Esko
author_facet Heiman, Damian
Kuusisto, Antti
Turunen, Esko
contents Neural networks are a fundamental aspect of modern artificial intelligence, playing a key role in various important machine learning architectures including transformers and graph neural networks. Recently, logical characterisations have been used to study the expressive power of many machine learning architectures, but logical characterisations of plain neural networks have received less attention. In this paper, we provide fuzzy logic characterisations of rational-weight ReLU-activated neural networks via two well-established fuzzy logics: Rational Pavelka Logic RPL (and extensions thereof) and (fragments of) $\mathit{L Π} \frac{1}{2}$. The activation values of the neural networks are allowed to be arbitrary real numbers. We also provide fuzzy logic characterisations of a generalised polynomial ring over $\mathbb{Q}$ in countably many variables where the use of the ReLU-function is permitted.
format Preprint
id arxiv_https___arxiv_org_abs_2605_03064
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neural networks as fuzzy logic formulas
Heiman, Damian
Kuusisto, Antti
Turunen, Esko
Logic in Computer Science
F.4.1; F.1.1; I.2.0
Neural networks are a fundamental aspect of modern artificial intelligence, playing a key role in various important machine learning architectures including transformers and graph neural networks. Recently, logical characterisations have been used to study the expressive power of many machine learning architectures, but logical characterisations of plain neural networks have received less attention. In this paper, we provide fuzzy logic characterisations of rational-weight ReLU-activated neural networks via two well-established fuzzy logics: Rational Pavelka Logic RPL (and extensions thereof) and (fragments of) $\mathit{L Π} \frac{1}{2}$. The activation values of the neural networks are allowed to be arbitrary real numbers. We also provide fuzzy logic characterisations of a generalised polynomial ring over $\mathbb{Q}$ in countably many variables where the use of the ReLU-function is permitted.
title Neural networks as fuzzy logic formulas
topic Logic in Computer Science
F.4.1; F.1.1; I.2.0
url https://arxiv.org/abs/2605.03064