LTKK Department of Information Technology Information processing research lab

NNGENETICS - Evolutionary Algorithms and Neural Networks

• Goals of the project
• News
• Documentation
• Download
• Links to other resources
• Contact information

Goal of this project is to analyze if genetic algorithms, especially differential evolution, can be used to train feed-forward neural networks. Disadvatanges and advantages of evolutionary methods are compared to traditional network training methods, mostly based on gradient information.

Project is finished. All the goals were met and results will be published in a scientific journal.

Contact authors for reprints.

1. Ilonen, J., Kamarainen, J.-K., Lampinen, J., Differential Evolution Training Algorithm for Feed-Forward Neural Networks, Neural Processing Letters 7, 1 (2003), 93-105.
   
   

Matlab(tm) source code (for scientific and non-profitable use only)

Differential evolution training algorithm for Neural-Network Toolbox (tm)	traindiffevol.m
Script for demonstration of the TRAINDIFFEVOL	demo01.m

To download data used in our experiments, explore data repositories from links section.

Differential evolution bibliographies by professor Jouni Lampinen

Local links by professor Jouni Lampinen

Differential Evolution page by Rainer Storn

Data repository: University of California

Dataset generator

Benchmark group on pattern recognition

Bibliography

[ML97] Masters, Timothy and Land, Walker (1997). A new training algorithm for the general regression neural network. 1997 IEEE International Conference on Systems, Man, and Cybernetics, Computational Cybernetics and Simulation., Volume: 3, pp. 1990-1994.

Jouni Lampinen	E-mail	WWW	Professor, responsible author, Lappeenranta University of Technology
Joni Kamarainen	E-mail	WWW	Researcher, Lappeenranta University of Technology
Jarmo Ilonen	E-mail	WWW	Research assistant, Lappeenranta University of Technology