Convergence of Online Gradient Method with a Penalty Term \\for BP Neural Network with Stochastic Inputs
Received:September 28, 2005  Revised:February 28, 2006
Key Words: BP neural networks   online gradient method   convergence   penalty term   stochastic inputs.  
Fund Project:the National Natural Science Foundation of China (10471017).
Author NameAffiliation
LU Hui-fang Department of Mathematics, Dalian University of Technology, Liaoning 116024, China
Department of Mathematics and Physics, Shandong Jiaotong University, Shandong 250023, China 
WU Wei Department of Mathematics, Dalian University of Technology, Liaoning 116024, China
 
LI Zheng-xue Department of Mathematics, Dalian University of Technology, Liaoning 116024, China
 
Hits: 3492
Download times: 1968
Abstract:
      In this paper, we present and discuss an online gradient method with a penalty term for three-layer BP neural networks. The input training examples are reset stochastically before the performance of each batch so that the learning is easy to jump off from local minima. The monotonicity and the convergence of deterministic nature are proved.
Citation:
DOI:10.3770/j.issn:1000-341X.2007.03.027
View Full Text  View/Add Comment