Dear Colleagues,
The paper referenced below is being presented now at the 9th Online
Conference on Soft Computing, session Algorithm Design. To see this and
other papers please go to:
http://www.cs.nmt.edu/~wsc9 or http://wsc9.softcomputing.net
Please join us and participate in the discussions.
See you there!
Candida Ferreira
Ferreira, C., Designing Neural Networks Using Gene Expression Programming.
9th Online World Conference on Soft Computing in Industrial Applications,
September 20 - October 8, 2004.
ABSTRACT:
An artificial neural network with all its elements is a rather complex
structure, not easily constructed and/or trained to perform a particular
task. Consequently, several researchers used Genetic Algorithms to evolve
partial aspects of neural networks, such as the weights, the thresholds, and
the network architecture. Indeed, over the last decade many systems have
been developed that perform total network induction. In this work it is
shown how the chromosomes of Gene Expression Programming can be modified so
that a complete neural network, including the architecture, the weights and
thresholds, could be totally encoded in a linear chromosome. It is also
shown how this chromosomal organization allows the training/adaptation of
the network using the evolutionary mechanisms of selection and modification,
thus providing an approach to the automatic design of neural networks. The
workings and performance of this new algorithm are tested on the
6-multiplexer and on the classical exclusive-or problems.
---
Candida Ferreira, Ph.D.
Chief Scientist, Gepsoft
http://www.gene-expression-programming.com/author.asp
GEP: Mathematical Modeling by an Artificial Intelligence
http://www.gene-expression-programming.com/gep/Books/index.asp
Modeling Software
http://www.gepsoft.com/gepsoft/
Get APS 3.0 Std free with the book!
|