A New Kind of Network? Review and Reference Implementation of Neural Cellular Automata

TL;DR

This paper reviews Neural Cellular Automata (NCA), a hybrid approach combining cellular automata with neural networks, and provides a modular framework and reference implementation in NCAtorch.

Contribution

It offers a comprehensive review of NCA research, introduces a unified framework and notation, and provides an open-source reference implementation.

Findings

NCA can learn complex CA update rules from data

The paper presents a modular framework for NCA modeling

Open-source code available at https://www.neural-cellular-automata.org/

Abstract

Stephen Wolfram proclaimed in his 2003 seminal work "A New Kind Of Science" that simple recursive programs in the form of Cellular Automata (CA) are a promising approach to replace currently used mathematical formalizations, e.g. differential equations, to improve the modeling of complex systems. Over two decades later, while Cellular Automata have still been waiting for a substantial breakthrough in scientific applications, recent research showed new and promising approaches which combine Wolfram's ideas with learnable Artificial Neural Networks: So-called Neural Cellular Automata (NCA) are able to learn the complex update rules of CA from data samples, allowing them to model complex, self-organizing generative systems. The aim of this paper is to review the existing work on NCA and provide a unified modular framework and notation, as well as a reference implementation in the open-source library NCAtorch. Supplementary materials, videos, and code are available at the project website: https://www.neural-cellular-automata.org/