Convergence of a Gradient Algorithm with Penalty for Training Two-layer Neural Networks

摘要：

In this paper, a squared penalty term is added to the conventional error function to improve the generalization of neural networks. A weight boundedness theorem and two convergence theorems are proved for the gradient learning algorithm with penalty when it is used for training a two-layer feedforward neural network. To illustrate above theoretical findings, numerical experiments are conducted based on a linearly separable problem and simulation results are presented. The abstract goes here.

作者: Hongmei Shao Lijun Liu Gaofeng Zheng

作者单位: College of Math. and Comput. Science China University of Petroleum Dongying, 257061, China Department of Mathematics Dalian Nationalities University Dalian, 116605, China JANA Solutions, Inc. Shiba 1-15-13, Minato-ku Tokyo, 105-0014, Japan

会议类型: 国际会议

会议名称: 2009 2nd IEEE International Conference on Computer Science and Information Technology(第二届计算机科学与信息技术国际会议 ICCSIT2009)

会议地点: 北京

会议语种:英文

页码: 2024-2027

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