A Hybrid of Artificial Fish Swarm Algorithm and Particle Swarm Optimization for Feedforward Neural Network Training

DOI

10.2991/iske.2007.174How to use a DOI?

Keywords

artificial fish-swarm algorithm; particle swarm optimization; artificial neural networks

Abstract

A hybrid of artificial fish swarm algorithm (AFSA) and particle swarm optimization (PSO) is used to training feedforward neural network. After the two algorithms are introduced respectively, the hybrid algorithm based on the two is expressed. The hybrid not only has the artificial fish behaviors of swarm and follow, but also takes advantage of the information of the particle. An experiment with a function approximation is simulated, which proves that the hybrid is more effective than AFSA and PSO.

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  - Huadong Chen
AU  - Shuzong Wang
AU  - Jingxi Li
AU  - Yunfan Li
PY  - 2007/10
DA  - 2007/10
TI  - A Hybrid of Artificial Fish Swarm Algorithm and Particle Swarm Optimization for Feedforward Neural Network Training
BT  - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
PB  - Atlantis Press
SP  - 1025
EP  - 1028
SN  - 1951-6851
UR  - https://doi.org/10.2991/iske.2007.174
DO  - 10.2991/iske.2007.174
ID  - Chen2007/10
ER  -