Emergent Dynamics in Neural Cellular Automata
This work addresses the problem of understanding and controlling dynamic patterns in NCA for researchers in generative models and computer graphics, but it is incremental as it builds on existing NCA applications.
The paper investigates the relationship between Neural Cellular Automata (NCA) architecture and emergent dynamics, finding that the disparity and proportionality between cell state channels and hidden neurons strongly correlate with motion strength, and proposes a design principle for dynamic NCA.
Neural Cellular Automata (NCA) models are trainable variations of traditional Cellular Automata (CA). Emergent motion in the patterns created by NCA has been successfully applied to synthesize dynamic textures. However, the conditions required for an NCA to display dynamic patterns remain unexplored. Here, we investigate the relationship between the NCA architecture and the emergent dynamics of the trained models. Specifically, we vary the number of channels in the cell state and the number of hidden neurons in the MultiLayer Perceptron (MLP), and draw a relationship between the combination of these two variables and the motion strength between successive frames. Our analysis reveals that the disparity and proportionality between these two variables have a strong correlation with the emergent dynamics in the NCA output. We thus propose a design principle for creating dynamic NCA.