A New RBF Neural Network Training Algorithm Based on PSO

摘要：

Based on the study of Radial Basis Function (RBF) neural network training algorithm and Particle Swarm Optimization (PSO) algorithm, a new RBF neural network training algorithm with modified PSO algorithm is formulated, in which a control gene is introduced into basis PSO algorithm. The algorithm can determine network structure and parameters, such as centers and widths of hidden units by combining with least square method. The new training algorithm is applied to the nonlinear system identification problem, comparing with hierachical genetic algorithm and orthogonal least squares algorithm (OLS), the simulation results illustrate its efficiency.

关键词： RBF neural network PSO algorithm least square method nonlinear system identification

作者: Dingxue Zhang Xinzhi Liu Zhihong Guan

作者单位: Control science and technology Department, Huazhong University of Science & Technology Wuhan, Hubei, 430074, China

会议类型: 国际会议

会议名称: 2006 International Symposium on Distributed Computing and Applications to Business,Engineering and Science(2006年国际电子、工程及科学领域的分布式计算应用学术研讨会)

会议地点: 杭州

会议语种:英文

页码: 731-734

在线出版日期: 2006-10-12（万方平台首次上网日期，不代表论文的发表时间）