Dynamic page based crossover in linear genetic programming

摘要

Page-based linear genetic programming (GP) is proposed in whichnindividuals are described in terms of a number of pages. Pages arenexpressed in terms of a fixed number of instructions, which is constantnfor all individuals in the population. Pairwise crossover results in thenswapping of single pages, and thus, individuals are of a fixed number ofninstructions. Head-to-head comparison with Tree-structured GP andnblock-based linear GP indicates that the page-based approach evolvesnsuccinct solutions without penalizing generalization ability