Gene Optimization: Computational Intelligence from the Natures and Micro-mechanisms of Hard Computational Systems

Abstract

Research on evolutionary theory and statistic physics has provided computer scientists with powerful methods for designing intelligent computational algorithms, such as simulated annealing, genetic algorithm, extremal optimization, etc. These techniques have been successfully applied to a variety of scientific and engineering optimization problems. However, these methodologies only dwell on the macroscopic behaviors (i.e., the global fitness of solutions) and never unveil the microscopic mechanisms of hard computational systems. Inspired by Richard Dawkins’s notion of the “selfish gene”, the paper explores a novel evolutionary computational methodology for finding high-quality solutions to hard computational systems. This method, called gene optimization, successively eliminates extremely undesirable components of sub-optimal solutions based on the local fitness of genes. A near-optimal solution can be quickly obtained by the self-organized evolutionary processes of computational systems. Simulations and comparisons based on the typical NP-complete traveling salesman problem demonstrate the effectiveness and efficiency of the proposed intelligent computational method.