Evolution of Intricate Long-Distance Communication Signals in Cellular Automata Using Genetic Programming
David André, Forrest H Bennett, John R. Koza · 2004
A cellular automata rule for the majority classification task was evolved using genetic programming with automatically defined functions. The genetically evolved rule has an accuracy of 82.326%. This level of accuracy exceeds that of the Gacs-Kurdyumov-Levin (GKL) rule, all other known human-written rules, and all other rules produced by known previous automated approaches. Our genetically evolved rule is qualitatively different from other rules in that it utilizes a finegrained internal representation of density information; it employs a large number of different domains and particles; and it uses an intricate set of signals for communicating information over large distances in time and space. 1. Introduction Local rules govern the important interactions of many animate and inanimate entities. The study of artificial life often focuses on how the simultaneous execution of a single relatively simple rule at many local sites leads to the emergence of interesting global behavior (Langt...