Saved in:
Bibliographic Details
Main Authors: Mommen, Wout, Keuninckx, Lars, Hartmann, Matthias, Wambacq, Piet
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.06173
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913932480872448
author Mommen, Wout
Keuninckx, Lars
Hartmann, Matthias
Wambacq, Piet
author_facet Mommen, Wout
Keuninckx, Lars
Hartmann, Matthias
Wambacq, Piet
contents We introduce a novel method for partial optimization of the connections in Deep Differentiable Logic Gate Networks (LGNs). Our training method utilizes a probability distribution over a subset of connections per gate input, selecting the connection with highest merit, after which the gate-types are selected. We show that the connection-optimized LGNs outperform standard fixed-connection LGNs on the Yin-Yang, MNIST and Fashion-MNIST benchmarks, while requiring only a fraction of the number of logic gates. When training all connections, we demonstrate that 8000 simple logic gates are sufficient to achieve over 98% on the MNIST data set. Additionally, we show that our network has 24 times fewer gates, while performing better on the MNIST data set compared to standard fully connected LGNs. As such, our work shows a pathway towards fully trainable Boolean logic.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06173
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Method for Optimizing Connections in Differentiable Logic Gate Networks
Mommen, Wout
Keuninckx, Lars
Hartmann, Matthias
Wambacq, Piet
Machine Learning
Artificial Intelligence
We introduce a novel method for partial optimization of the connections in Deep Differentiable Logic Gate Networks (LGNs). Our training method utilizes a probability distribution over a subset of connections per gate input, selecting the connection with highest merit, after which the gate-types are selected. We show that the connection-optimized LGNs outperform standard fixed-connection LGNs on the Yin-Yang, MNIST and Fashion-MNIST benchmarks, while requiring only a fraction of the number of logic gates. When training all connections, we demonstrate that 8000 simple logic gates are sufficient to achieve over 98% on the MNIST data set. Additionally, we show that our network has 24 times fewer gates, while performing better on the MNIST data set compared to standard fully connected LGNs. As such, our work shows a pathway towards fully trainable Boolean logic.
title A Method for Optimizing Connections in Differentiable Logic Gate Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2507.06173