Finite Convergence of On-line BP Neural Networks with Linearly Separable Training Patterns
Received:October 10, 2004  
Key Words: nonlinear feedforward neural networks   online BP algorithms   finite convergence   linearly separable training patterns.  
Fund Project:the National Natural science Foundation of China (10471017), and the Basic Research Program of the National Defence Committee of Science, Technology and Industry of China (K1400060406)
Author NameAffiliation
SHAO Zhi-qiong Dept. of Appl. Math., Dalian University of Technology, Liaoning 116023, China 
WU Wei Dept. of Appl. Math., Dalian University of Technology, Liaoning 116023, China 
YANG Jie Dept. of Appl. Math., Dalian University of Technology, Liaoning 116023, China 
Hits: 3590
Download times: 2753
Abstract:
      In this paper we prove a finite convergence of online BP algorithms for nonlinear feedforward neural networks when the training patterns are linearly separable.
Citation:
DOI:10.3770/j.issn:1000-341X.2006.03.004
View Full Text  View/Add Comment  
  Copyright © Journal of Mathematical Research with Applications
Sponsored by：Dalian University of Technology, China Society for Industrial and Applied Mathematics
Address：No.2 Linggong Road, Ganjingzi District, Dalian City, Liaoning Province, P. R. China , Postal code ：116024
Service Tel：86-411-84707392 Email：jmre@dlut.edu.cn
Designed by Beijing E-tiller Co.,Ltd.
Due to security factors, early browsers cannot log in. It is recommended to log in with IE10, IE11, Google, Firefox, and 360 new browsers.