BP neural network optimized with PSO algorithm and its application in forecasting

摘要：

An approach that neural network optimized with PSO algorithm is proposed in the paper. Unlike conventional training method with gradient descent method only, this paper introduces a hybrid training algorithm by combining the PSO and BP algorithm. The PSO is used to optimize the initial parameters of the BP neural network, including the weights and biases. It can effectively better the cases that network is easily trapped to a local optimum and has a slow velocity of convergence. The experiment results show the method in the paper above conventional one has greater improvement in both accuracy and velocity of convergence for BP neural network.

关键词： BP Neural Network training algorithm Particle Swarm Optimization Evolution Computation Forecasting.

作者: Wen Guo Yizheng Qiao Haiyan Hou

作者单位: School of Control Science and Engineering, Shandong University Jinan, 250061, P.R. China

会议类型: 国际会议

会议名称: 2006 IEEE International Conference on Information Acquisition

会议地点: 山东威海

会议语种:英文

页码: 617-621

在线出版日期: 2006-08-20（万方平台首次上网日期，不代表论文的发表时间）