The Class Algorithm: Evolution Based on Division of Labor and Specialization

Abstract

This paper proposes the class algorithm, a new type of evolutionary algorithm. The methodology is inspired by the concepts of division of labor and specialization. Individuals form subpopulations of different classes, where each class has its own characteristics. The entire population evolves through influences among individuals within and between the different subpopulations. The proposed approach can be applied in both continuous and discrete problem domains. The performance of the class algorithm surpasses other evolutionary algorithms for many test functions of single-objective continuous optimization benchmark problems. The class algorithm also shows a competent ability to solve the large-scale discrete optimization problems.