Optimizing feed-forward neural networks using cascaded genetic algorithm

Lin-xia Zhou; Ming Li; Xiaoqin Yang

doi:10.1117/12.538873

25 September 2003 Optimizing feed-forward neural networks using cascaded genetic algorithm

Lin-xia Zhou, Ming Li, Xiaoqin Yang

Proceedings Volume 5286, Third International Symposium on Multispectral Image Processing and Pattern Recognition; (2003) https://doi.org/10.1117/12.538873
Event: Third International Symposium on Multispectral Image Processing and Pattern Recognition, 2003, Beijing, China

Abstract

A novel method of optimizing feed-forward neural networks using cascaded genetic algorithm is proposed in this paper. It adopts a hybrid encoding method, which architectures and connection weights vector of neural networks are encoded into binary code and real-value code respectively. The proposed optimizing method includes two cascaded evolutionary procedures in which the first mainly plays the role of fast search in constrained area and the second extends global exploration ability. The proposed method has represented a particular compromise between exploitation and exploration of searching optimized neural networks and enhanced the global search ability while using less computation. The experimental results have shown its good performance.

Citation Download Citation

Lin-xia Zhou, Ming Li, and Xiaoqin Yang "Optimizing feed-forward neural networks using cascaded genetic algorithm", Proc. SPIE 5286, Third International Symposium on Multispectral Image Processing and Pattern Recognition, (25 September 2003); https://doi.org/10.1117/12.538873

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available