Acceleration of Grammatical Evolution with Multiple Chromosome by Using Stochastic Schemata Exploiter

Abstract

Grammatical Evolution (GE), which is one of evolutionary computations, is designed to find the function or the executable program or program fragment that satisfies the design objective. Candidate solutions are described in bit-string or the set of decimal numbers. The translation process from the genotype (bit-string) to the phenotype (function or program) is defined in the list of the translation rules. Candidate solutions are evolved according to the Simple Genetic Algorithm. There are three issues in Grammatical Evolution process; genotype definition, translation rules, and search algorithm. Grammatical Evolution with Multiple Chromosomes (GEMC) is designed for improving the genotype definition. The aim of this study is to improve the search algorithm from Simple Genetic Algorithm to Stochastic Schemata Exploiter for improving the convergence speed. The proposal algorithm “Grammatical Evolution with Multiple Chromosome by Using Stochastic Schemata Exploiter (GEMC-SSE)” is applied for the symbolic regression problem in order to discuss the search performance. The numerical results show that the proposal algorithm has faster convergence speed than the original GEMC.