Self-Replication, Spontaneous Mutations, and Exponential Genetic Drift in Neural Cellular Automata
This work shows evolutionary dynamics in a new computational framework, potentially advancing artificial life and evolutionary computation research.
The paper demonstrates that Neural Cellular Automata can exhibit self-replicating patterns with spontaneous, inheritable mutations and exponential genetic drift away from ancestral patterns, even without explicit training for these properties, increasing the space of variations for Open Ended Evolution.
This paper reports on patterns exhibiting self-replication with spontaneous, inheritable mutations and exponential genetic drift in Neural Cellular Automata. Despite the models not being explicitly trained for mutation or inheritability, the descendant patterns exponentially drift away from ancestral patterns, even when the automaton is deterministic. While this is far from being the first instance of evolutionary dynamics in a cellular automaton, it is the first to do so by exploiting the power and convenience of Neural Cellular Automata, arguably increasing the space of variations and the opportunity for Open Ended Evolution.