A Path to Universal Neural Cellular Automata

TL;DR

This paper demonstrates that neural cellular automata can be trained via gradient descent to perform universal computation tasks in a continuous domain, including emulating neural networks for digit classification.

Contribution

It introduces a framework for training neural cellular automata to achieve universal computation in continuous settings, bridging cellular automata theory and machine learning.

Findings

Successfully trained neural cellular automata to perform matrix operations.

Emulated a neural network solving MNIST within cellular automata.

Established a foundation for continuous universal computation in neural automata.

Abstract

Cellular automata have long been celebrated for their ability to generate complex behaviors from simple, local rules, with well-known discrete models like Conway's Game of Life proven capable of universal computation. Recent advancements have extended cellular automata into continuous domains, raising the question of whether these systems retain the capacity for universal computation. In parallel, neural cellular automata have emerged as a powerful paradigm where rules are learned via gradient descent rather than manually designed. This work explores the potential of neural cellular automata to develop a continuous Universal Cellular Automaton through training by gradient descent. We introduce a cellular automaton model, objective functions and training strategies to guide neural cellular automata toward universal computation in a continuous setting. Our experiments demonstrate the successful training of fundamental computational primitives - such as matrix multiplication and transposition - culminating in the emulation of a neural network solving the MNIST digit classification task directly within the cellular automata state. These results represent a foundational step toward realizing analog general-purpose computers, with implications for understanding universal computation in continuous dynamics and advancing the automated discovery of complex cellular automata behaviors via machine learning.