Convergence of Online Gradient Method with Penalty for BP Neural Networks |
| |
Authors: | Shao Hong-mei Wu Wei Liu Li-jun |
| |
Institution: | 1. College of Mathematics and Computational Science;China University of Petroleum;Dongying;Shandong;257061;2. Department of Applied Mathematics;Dalian University of Technology;Dalian;Liaoning;116024;3. Department of Mathematics;Dalian Nationalities University;116605 |
| |
Abstract: | Online gradient method has been widely used as a learning algorithm for training feedforward neural networks. Penalty is often introduced into the training procedure to improve the generalization performance and to decrease the magnitude of network weights. In this paper,some weight boundedness and deterministic convergence theorems are proved for the online gradient method with penalty for BP neural network with a hidden layer,assuming that the training samples are supplied with the network in a fixed orde... |
| |
Keywords: | convergence online gradient method penalty monotonicity |
本文献已被 CNKI 维普 万方数据 等数据库收录! |