Share Email Print

Proceedings Paper

Adaptable multiple neural networks using evolutionary computation
Author(s): Sunghwan Sohn; Cihan H. Dagli
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The architecture of an artificial neural network has a significant influence on its performance. For a given problem, the proper architecture is found by trial and error. This approach is time consuming and may not always produce the optimal network. In this reason, we can apply the evolutionary computation such as genetic algorithm to implement the automation of network's structure as well as the biological inspiration in neural networks to successfully adapt varying input environment. Moreover, we examine the performance of combining multiple evolving networks that are more likely to model the neurophysiology of the human brain. In the combining module, all individual networks or selected individual networks in the population are used. Also, the dynamic data set is used to provide the networks with diversity and generalization. In this model, each evolving individual network is designed to have a specific feature set and neuron connection links for given data. Then, the results are combined through the combining module to improve the generalization performance of the single network. The Iris and Austrian credit data are used in the experiment.

Paper Details

Date Published: 11 March 2002
PDF: 9 pages
Proc. SPIE 4739, Applications and Science of Computational Intelligence V, (11 March 2002); doi: 10.1117/12.458706
Show Author Affiliations
Sunghwan Sohn, Univ. of Missouri/Rolla (United States)
Cihan H. Dagli, Univ. of Missouri/Rolla (United States)

Published in SPIE Proceedings Vol. 4739:
Applications and Science of Computational Intelligence V
Kevin L. Priddy; Paul E. Keller; Peter J. Angeline, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?