An Improved PSO-BP Network Model

An improved network model to adjust weights of BP network based on particle swarm optimization(PSO) was proposed. The fuzzy control was used to assign the different weight to PSO and BP algorithm during different periods. PSO algorithm plays a main role in the previous evolution period, and BP algorithm plays a vital roal in later period. The model can overcome the slow convergence and easily getting into the local extremum of basic BP algorithm, and can also improve the learning ability and generalization ability with a higher precision. The simulation results show that the improved PSOBP network model has higher accuracy and quicker response than the traditional model.