Adversarial Reprogramming of Neural Cellular Automata

Abstract

Neural Cellular Automata (NCA) models have shown remarkable capacity for pattern formation and complex global behaviors stemming from local coordination. However, in the original implementation of NCA, cells are incapable of adjusting their own orientation, and it is the responsibility of the model designer to orient them externally. A recent isotropic variant of NCA (Growing Isotropic Neural Cellular Automata) makes the model orientation-independent -cells can no longer tell up from down, nor left from right -by removing its dependency on perceiving the gradient of spatial states in its neighborhood. In this work, we revisit NCA with a different approach: we make each cell responsible for its own orientation by allowing it to "turn" as determined by an adjustable internal state. The resulting Steerable NCA contains cells of varying orientation embedded in the same pattern. We observe how, while Isotropic NCA are orientationagnostic, Steerable NCA have chirality: they have a predetermined left-right symmetry. We therefore show that we can train Steerable NCA in similar but simpler ways than their Isotropic variant by: (1) breaking symmetries using only two seeds, or (2) introducing a rotation-invariant training objective and relying on asynchronous cell updates to break the up-down symmetry of the system.

Carle's Game: An Open-Ended Challenge in Exploratory Machine Creativity

“…All other cells transition to a state of 0. characteristics of complexity and universal computation of many CA [8], [9], [54], CA make a good substrate for modeling physical phenomena [51]. Recent work in differentiable neural CA offer interesting possibilities for modern machine learning [26], [27], [31], [32].…”

Self-Replication, Spontaneous Mutations, and Exponential Genetic Drift in Neural Cellular Automata

“…While they have not yet been used to model evolution, NCA have proven useful to implement biology-like functions in artificial patterns. Patterns that grow from a seed (Mordvintsev et al (2020)), similar to the development of biological organisms from egg to adult form; patterns that self-repair (Mordvintsev et al (2020); Horibe et al (2021)); patterns that undergo metamorphosis (Najarro et al (2022)), or parasite and highjack other patterns (Randazzo et al (2021)). Many non-neural cellular automata have explored the possibility of (Open Ended) evolution, with several organisms controlled by one automaton (Sayama (1999); Oros and Nehaniv (2007)).…”