Abstract
Neural Cellular Automata (NCA) are a powerful combination of machine learning and mechanistic modelling. We train NCA to learn complex dynamics from time series of images and Partial Differential Equation (PDE) trajectories. Our method is designed to identify underlying local rules that govern large scale dynamic emergent behaviours. Previous work on NCA focuses on learning rules that give stationary emergent structures. We extend NCA to capture both transient and stable structures within the same system, as well as learning rules that capture the dynamics of Turing pattern formation in nonlinear PDEs. We demonstrate that NCA can generalise very well beyond their PDE training data, we show how to constrain NCA to respect given symmetries, and we explore the effects of associated hyperparameters on model performance and stability. Being able to learn arbitrary dynamics gives NCA great potential as a data driven modelling framework, especially for modelling biological pattern formation.
Funder
Engineering and Physical Sciences Research Council
Publisher
Public Library of Science (PLoS)
Reference54 articles.
1. Emergence phenomena in self-organizing systems: a systematic literature review of concepts, researches, and future prospects;S Kalantari;Journal of Organizational Computing and Electronic Commerce,2020
2. Mathematical Games;M Gardner;Scientific American,1970
3. A Brief History of Cellular Automata;P Sarkar;ACM Comput Surv,2000
4. A Bibliographic Review of Cellular Automaton Publications in the Last 50 Years;Y Zhuang;Journal of Cellular Automata,2017
5. A living mesoscopic cellular automaton made of skin scales;L Manukyan;Nature,2017