A Modified Differential Evolution Algorithm for Optimization Neural Network

DOI

10.2991/iske.2007.30How to use a DOI?

Keywords

evolution strategies; neural network; 1/2 rule; evolution algorithm; differential evolution

Abstract

A Modified Differential Evolution (MDE) was proposed, which based on the basic Differential Evolution (DE) algorithm principle and implementing framework of DE. Optimizing the initial individuals with the 1/2 rule, and then introducing the reorganization of Evolution Strategies during the period of mutation procedures. The MDE was used to optimize the weights of the feed-forward multilayer neural network, and compared with the basic DE and BP algorithm with momentum term. Finally, the numerical simulation results show that this method has good quality of high-speed global convergence and effectively improves the precision and convergence speed for feed-forward multilayer neural network, it has been proven the effectively and feasibility.

Copyright

© 2007, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ning Guiying
AU  - Zhou Yongquan
PY  - 2007/10
DA  - 2007/10
TI  - A Modified Differential Evolution Algorithm for Optimization Neural Network
BT  - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
PB  - Atlantis Press
SP  - 173
EP  - 177
SN  - 1951-6851
UR  - https://doi.org/10.2991/iske.2007.30
DO  - 10.2991/iske.2007.30
ID  - Guiying2007/10
ER  -