中国教育图书进出口有限公司

[期刊论文]

Magnified gradient function in adaptive learning: the MGFPROP algorithm

作者：	Sin-Chun Ng;Chi-Chung Cheung;Shu-Hung Leung;

出版年：2001

页码：42 - 42

出版社：Institution of Engineering and Technology (IET)

摘要：

A new algorithm is proposed to solve the “flat spot” problem in backpropagation neural networks by magnifying the gradient function. Simulation results show that, in terms of the convergence rate and the percentage of global convergence, the new algorithm consistently outperforms other traditional methods

关键字：

backpropagation; convergence; feedforward neural nets; MGFPROP algorithm; adaptive learning; backpropagation neural networks; convergence rate; flat spot problem solution; global convergence; magnified gradient function

去购买

原文链接

所属期刊

Electronics Letters

ISSN: 0013-5194

来自：Institution of Engineering and Technology (IET)