Search papers, labs, and topics across Lattice.
This paper reviews Neural Cellular Automata (NCA), a class of models combining Cellular Automata with learnable neural networks for modeling complex systems. It synthesizes existing NCA research, providing a unified notation and modular framework. The authors also release NCAtorch, an open-source library providing a reference implementation of the reviewed methods.
Neural Cellular Automata, blending Wolfram's recursive programs with neural networks, offer a fresh perspective on modeling complex, self-organizing systems.
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.