Research on several problems in BP neural network application

摘要：

Four problems existing in BP neural network practical application are discussed in this paper: slow converging speed, converging at local minimum, overtraining and poor extrapolating capacity. Comparing advantages and disadvantage of several acceleration algorithms, the paper provides the suggestions of solving those problems. The paper also advances a forecasting model of monthly irrigation return flow based on BP neural network is advanced as a case study.

关键词： BP neural network acceleration algorithm local minimum overtraining extrapolating ability

作者: Huang Duo Zhao Xinyu

作者单位: School of Business Administration Xian University of Technology Xian, China Institute of Water Resources and Hydro-electric Engineering Xian University of Technology Xian, Ch

会议类型: 国际会议

会议名称: 第三届IEEE无线通讯、网络技术暨移动计算国际会议

会议地点: 上海

会议语种:英文

在线出版日期: 2007-09-21（万方平台首次上网日期，不代表论文的发表时间）