A New Kind of Network? Review and Reference Implementation of Neural Cellular Automata
For researchers in complex systems and machine learning, this work offers a structured overview and practical tools to advance NCA research, though it is primarily a review and implementation effort.
This paper reviews Neural Cellular Automata (NCA), providing a unified framework and reference implementation (NCAtorch) to standardize notation and facilitate further research.
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.