Study on RBF neural network based on swarm intelligence

Abstract

Particle swarm optimization (PSO) is one of swarm intelligence. It was modified by escape of the particle velocity, and a self-adaptive PSO (SAPSO) was proposed to overcome the PSO shortcomings of the premature convergence and the local optimization. The SAPSO is combined with radial basis function (RBF) neural network to form a SAPSON hybrid algorithm. Compared with radial basis function neural network, SAPSON has less adjustable parameters, faster convergence speed, global optimization and higher identification precision in the numerical experiment.