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

TL;DR

This paper presents Differentiable Logic Cellular Automata, a hybrid model combining neural automata and logic gates, enabling learning and generation of complex patterns with robustness and generalization, bridging discrete automata and neural networks.

Contribution

It introduces a novel differentiable logic cellular automata framework that learns local update rules and generates diverse patterns, advancing programmable matter and robust computing.

Findings

Successfully learned Conway's Game of Life rules

Generated noise-resistant checkerboard patterns

Produced complex multi-color patterns and shapes

Abstract

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 model are differentiable logic gates, combined into a circuit. During training, the model is fully end-to-end differentiable allowing gradient-based training, and at inference time it operates in a fully discrete state space. This enables learning local update rules for cellular automata while preserving their inherent discrete nature. We demonstrate the versatility of our approach through a series of milestones: (1) fully learning the rules of Conway's Game of Life, (2) generating checkerboard patterns that exhibit resilience to noise and damage, (3) growing a lizard shape, and (4) multi-color pattern generation. Our model successfully learns recurrent circuits capable of generating desired target patterns. For simpler patterns, we observe success with both synchronous and asynchronous updates, demonstrating significant generalization capabilities and robustness to perturbations. We make the case that this combination of DLGNs and NCA represents a step toward programmable matter and robust computing systems that combine binary logic, neural network adaptability, and localized processing. This work, to the best of our knowledge, is the first successful application of differentiable logic gate networks in recurrent architectures.