Identity Increases Stability in Neural Cellular Automata
This work addresses stability issues for researchers studying artificial organism growth in NCAs, but it is incremental as it builds on existing NCA methods with a simple modification.
The paper tackled the stability problem in Neural Cellular Automata (NCA)-grown organisms, which often break down or exhibit tumor-like growth, by introducing an 'identity' layer with constraints during training, resulting in more stable organisms with emergent movement observed in models with multiple identity values.
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