Constructional Selection, Methylation and Adaptable Representation: Preliminary Findings

This paper investigates the adaptability of genotypes produced by a modified genome growth algorithm (MGG) in a genetic algorithm. MGG uses constructional selection, a genome growth strategy modeled on the evolution of the biological genome [1]. Experiments did not favor the more costly MGG genotypes. This paper also proposes a new type of mutation operator: meth, which is loosely based on DNA methylation. Experiments suggest the utility of ‘methylation’ to improve the adaptability of representations and to build robust and adaptable digital structures.