On-Line Learning Neural Network and Its Application

摘要：

Based on some analysis of the standby back propagation neural network in some literatures, this paper puts forward an on-line learning neural network. Neural network consists of working sets and standby sets of implicit strata real-time adjusted set number. Standby sets changed into working sets when the need of neural network relearned arised. The benefit of the change is that the neural network only update weight of sets between new nets and output nets, and the neural network fast learns new input sample when previous information are maintained. Calculations results show that the algorithms proposed in the paper are valid and correct.

关键词： BP neural network optimize control genetic algorithm chaos algorithm

作者: YANG Lina ZHAO Xiufeng ZHANG Jie

作者单位: Institute of Electronic Technology, P.L.A Information Engineering University, Zhengzhou, Henan China, 450004

会议类型: 国际会议

会议名称: 第八届国际测试技术研讨会(8th International Symposium on Test and Measurement)

会议地点: 重庆

会议语种:英文

页码: 1462-1465

在线出版日期: 2009-08-01（万方平台首次上网日期，不代表论文的发表时间）