Evolving two-dimensional cellular automata to perform density classification: A report on work in progress

We present results from experiments in which a genetic algorithm (GA) is used to evolve two dimensional cellular automata (CA) to perform a particular computational task (“density classification”) that requires globally-coordination information processing. The results are similar to that of earlier work on evolving one-dimensional CAs. The behavior of the evolved two-dimensional CAs is analyzed, and their performance is compared with that of several hand-designed two-dimensional CAs.