Neural Network Research Using Particle Swarm Optimization

摘要：

In view of the artificial neural network weights training problem,this paper proposed a method to optimize the networks structure parameters and regularization coefficient using two-layer Particle Swarm Optimization (PSO).This algorithm was applied to train Adaline network Compared with fixed regularization coefficient method and Sliding Mode Variable Structure optimization method,the result showed that it had the advantages of high precision and strong ability of generalization.

关键词： Two-layer Particle Swarm Neural network Regularization

作者: Yahui Wang Zhifeng Xia Yifeng Huo

作者单位: School of Electronic & Information Engineering of Beijing University of Civil Engineering and Archit Technology College of Beijing Forestry University Beijing china

会议类型: 国际会议

会议名称: 2010 4th International Conference on Intelligent Information Techonlogy Application(第四届智能信息技术应用国际学术研讨会 IITA 2010)

会议地点: 秦皇岛

会议语种:英文

页码: 27-30

在线出版日期: 2010-11-05（万方平台首次上网日期，不代表论文的发表时间）