Identity Increases Stability in Neural Cellular Automata

TL;DR

This paper introduces an 'identity' layer in Neural Cellular Automata to enhance the stability of artificial organisms, enabling more consistent growth and emergent behaviors, and facilitating future studies of cellular interactions.

Contribution

It proposes a novel 'identity' layer with constraints during training to improve NCA stability and demonstrates emergent movement and interaction among stable organisms.

Findings

NCAs with identity layers are more stable than original models

A single identity value suffices for increased stability

Emergent movement observed in stable organisms

Abstract

Neural Cellular Automata (NCAs) offer a way to study the growth of two-dimensional artificial organisms from a single seed cell. From the outset, NCA-grown organisms have had issues with stability, their natural boundary often breaking down and exhibiting tumour-like growth or failing to maintain the expected shape. In this paper, we present a method for improving the stability of NCA-grown organisms by introducing an 'identity' layer with simple constraints during training. Results show that NCAs grown in close proximity are more stable compared with the original NCA model. Moreover, only a single identity value is required to achieve this increase in stability. We observe emergent movement from the stable organisms, with increasing prevalence for models with multiple identity values. This work lays the foundation for further study of the interaction between NCA-grown organisms, paving the way for studying social interaction at a cellular level in artificial organisms. Code/Videos available at: https://github.com/jstovold/ALIFE2025