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 Name | Affiliation | 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 |