Home|News|Literature|Journal|Instruction|Forum|Member|Introduction

Chinese  Old version

By    In    Search 

  HomeContents of Chinese Journal of Mechanical Engineering (English Edition),2000 Supp.STUDY ON EVOLUTIONARY NEURAL NETWORKS AND SOFTWARE DEVELOPMENT WITH JAVA
 STUDY ON EVOLUTIONARY NEURAL NETWORKS

AND SOFTWARE DEVELOPMENT WITH JAVA*

 

Zhu Yan  Guo Xiaoting  Chen Jian

 School of Economics and Management, Qinghua University

 

Abstract:  Based on the genetic algorithms(GAs), an automatic design and optimizing method called GMNN (Genetic Multilayer Neural Network) for feedforward multilayer neural networks is put forward. Based on the analysis of historical structure design methods of neural networks, the special genetic encoding representations are discussed, and a fitness function is defined also. Some special genetic operations are designed according to the problem. In addition, simulated annealing algorithms, BP algorithms and niche technology is also used to accelerate the convergence rate and improve the generalization of the solution. The elementary results of the experiments indicate that this method can find the satisfied network comparatively fast and the generalization performance of the network that we got is good. In the process of the software development, Java language is adopted considering the underlying parallel of the Gas and neural networks, and the realizing methods of parallel evolution neural networks are discussed also.

Key words: Artificial neural network  BP model  Evolutionary computation  Genetic algorithms


* This project is partly supported by National Natural Science Foundation of China (69674037 and 79825102)

 

Open or Download Full Text of this Paper (PDF File)

About us-Contact us-Site map-Advertisement service-Cooperation-Legal statement

Address: 22 Baiwanzhuang Dajie, Beijing 100037 China    Tel: 8610-88379907    Fax: 8610-68994557

E-mail: cjme@mail.machineinfo.gov.cn  http: //www.cjmenet.com
©2006 Editorial Office of CJME. All Right Reserved