Convolutional Differentiable Logic Gate Networks

2024-11-07 · Felix Petersen, Hilde Kuehne, Christian Borgelt, Julian Welzel, Stefano Ermon

With the increasing inference cost of machine learning models, there is a growing interest in models with fast and efficient inference. Recently, an approach for learning logic gate networks directly via a differentiable relaxation was proposed. Logic gate networks are faster than conventional neural network approaches because their inference only requires logic gate operators such as NAND, OR, and XOR, which are the underlying building blocks of current hardware and can be efficiently executed. We build on this idea, extending it by deep logic gate tree convolutions, logical OR pooling, and residual initializations. This allows scaling logic gate networks up by over one order of magnitude and utilizing the paradigm of convolution. On CIFAR-10, we achieve an accuracy of 86.29% using only 61 million logic gates, which improves over the SOTA while being 29x smaller.

📄 PDF Abstract BibTeX arXiv:2411.04732

Code (1)

felix-petersen/difflogic 공식 구현 pytorch

Emulating Non-Differentiable Metrics via Knowledge-Guided Learning: Introducing the Minkowski Image Loss

2026-04-13 · Filippo Quarenghi, Ryan Cotsakis, Tom Beucler arxiv

The ``differentiability gap'' presents a primary bottleneck in Earth system deep learning: since models cannot be trained directly on non-differentiable scientific metrics and must rely on smooth proxies (e.g., MSE), the…

Deep Differentiable Logic Gate Networks

2022-10-15 · Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen

Recently, research has increasingly focused on developing efficient neural network architectures. In this work, we explore logic gate networks for machine learning tasks by learning combinations of logic gates. These net…

CPU Efficient Neural Network

A Scalable, Interpretable, Verifiable & Differentiable Logic Gate Convolutional Neural Network Architecture From Truth Tables

2022-08-18 · Adrien Benamira, Tristan Guérand, Thomas Peyrin, Trevor Yap 외

We propose $\mathcal{T}$ruth $\mathcal{T}$able net ($\mathcal{TT}$net), a novel Convolutional Neural Network (CNN) architecture that addresses, by design, the open challenges of interpretability, formal verification, and…

Fairness Logical Reasoning

Recurrent Deep Differentiable Logic Gate Networks

2025-08-08 · Simon Bührer, Andreas Plesner, Till Aczel, Roger Wattenhofer arxiv

While differentiable logic gates have shown promise in feedforward networks, their application to sequential modeling remains unexplored. This paper presents the first implementation of Recurrent Deep Differentiable Logi…

Differentiable Logic Cellular Automata: From Game of Life to Pattern Generation

2025-06-05 · Pietro Miotti, Eyvind Niklasson, Ettore Randazzo, Alexander Mordvintsev

This paper introduces Differentiable Logic Cellular Automata (DiffLogic CA), a novel combination of Neural Cellular Automata (NCA) and Differentiable Logic Gates Networks (DLGNs). The fundamental computation units of the…