By Topic

A novel training algorithm of genetic neural networks and its application to classification

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $31
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Jianhua, Xiao ; School of Mechanics, Huazhong University of Science & Technology, Wuhan 430074, P. R. China Institute of Intelligence Technology & Systems, Wuyi University, Jiangmen 529020, P. R. China ; Jinpei, Wu ; Shuzi, Yang

First of all, this paper discusses the drawbacks of multilayer percept ron (MLP), which is trained by the traditional back propagation (BP) algorithm and used in a special classification problem. A new training algorithm for neural networks based on genetic algorithm and BP algorithm is developed. The difference between the new training algorithm and BP algorithm in the ability of nonlinear approaching is expressed through an example, and the application foreground is illustrated by an example.

Published in:

Systems Engineering and Electronics, Journal of  (Volume:12 ,  Issue: 3 )