The Genetic Programming of an Artificial Nervous System

This paper shows that it is possible to build (evolve) hyper-complex systems such as an artificial nervous system, despite the fact that the interactions or dynamics of these systems are (probably) too complex to be analyzed. Genetic Programming (GP) is “applied evolution”, i.e. using the Genetic Algorithm (GA) to evolve hyper-complex systems. This paper presents results of the “LIZZY Project”, proposed in earlier papers concerning the construction of an artificial nervous system in a Lizard-like artificial creature (or “biot”, i.e. biological robot) capable of reacting to other “creatures” in its environment in the form of predators, prey, and mates.