Mixtures of Neural Cellular Automata: A Stochastic Framework for Growth Modelling and Self-Organization
This work addresses the problem of modeling stochastic self-organizing processes in life sciences, offering a novel framework for researchers in computational biology and AI, though it is incremental by extending NCAs with mixture models.
The paper tackled the limitation of deterministic Neural Cellular Automata (NCAs) in capturing stochasticity in biological systems by proposing Mixtures of Neural Cellular Automata (MNCA), a framework that incorporates probabilistic rules and noise. Results showed MNCAs achieve superior robustness to perturbations, better recapitulate real biological growth patterns, and provide interpretable rule segmentation in domains like tissue growth and image segmentation.
Neural Cellular Automata (NCAs) are a promising new approach to model self-organizing processes, with potential applications in life science. However, their deterministic nature limits their ability to capture the stochasticity of real-world biological and physical systems. We propose the Mixture of Neural Cellular Automata (MNCA), a novel framework incorporating the idea of mixture models into the NCA paradigm. By combining probabilistic rule assignments with intrinsic noise, MNCAs can model diverse local behaviors and reproduce the stochastic dynamics observed in biological processes. We evaluate the effectiveness of MNCAs in three key domains: (1) synthetic simulations of tissue growth and differentiation, (2) image morphogenesis robustness, and (3) microscopy image segmentation. Results show that MNCAs achieve superior robustness to perturbations, better recapitulate real biological growth patterns, and provide interpretable rule segmentation. These findings position MNCAs as a promising tool for modeling stochastic dynamical systems and studying self-growth processes.