Pareto RBF networks using multiobjective evolutionay computation

Abstract

In this paper, RBF network structure selection method based on the multi--objective evolutionary algorithms is considered.The candidates of RBF network structure are encoded into the binary coded chromosomes. Then, they evolve toward Pareto--optimal front defined by the several objective functions corresponding to the model accuracy and model complexity. An ensemble network constructed by such Pareto--optimal networks is also addressed in this paper. The properties of the proposed ensemble network is discussed by numerical simulation results in the case of existence of outliers or lack of data, and compared with one selected in the sense of information criteria.