Please use this identifier to cite or link to this item: http://ktisis.cut.ac.cy/handle/10488/7174
Title: Coupling weight elimination with genetic algorithms to reduce network size and preserve generalization
Authors: Georgiopoulos, Michael N.
Bebis, George N.
Kasparis, Takis 
Keywords: Neural networks
Genetic algorithms
Pruning
Databases
Issue Date: 1997
Publisher: Elsevier
Source: Neurocomputing, 1997, Volume 17, Issue 3-4, Pages 167-194
Abstract: Recent theoretical results support that decreasing the number of free parameters in a neural network (i.e., weights) can improve generalization. These results have triggered the development of many approaches which try to determine an 'appropriate' network size for a given problem. The main goal has been to find a network size just large enough to capture the general class properties of the data. In some cases, however, network size is not reduced significantly or the reduction is satisfactory but generalization is affected. In this paper, we propose the coupling of genetic algorithms with weight elimination. Our objective is not only to significantly reduce network size, by pruning larger size networks, but also to preserve generalization, that is, to come up with pruned networks which generalize as good or even better than their unpruned counterparts. The innovation of our work relies on a fitness function which uses an adaptive parameter to encourage reproduction of networks having small size and good generalization. The proposed approach has been tested using both artificial and real databases demonstrating good performance. Recent theoretical results support that decreasing the number of free parameters in a neural network (i.e., weights) can improve generalization. These results have triggered the development of many approaches which try to determine an `appropriate' network size for a given problem. The main goal has been to find a network size just large enough to capture the general class properties of the data. In some cases, however, network size is not reduced significantly or the reduction is satisfactory but generalization is affected. In this paper, we propose the coupling of genetic algorithms with weight elimination. Our objective is not only to significantly reduce network size, by pruning larger size networks, but also to preserve generalization, that is, to come up with pruned networks which generalize as good or even better than their unpruned counterparts. The innovation of our work relies on a fitness function which uses an adaptive parameter to encourage reproduction of networks having small size and good generalization. The proposed approach has been tested using both artificial and real databases demonstrating good performance.
URI: http://ktisis.cut.ac.cy/handle/10488/7174
ISSN: 09252312
DOI: 10.1016/S0925-2312(97)00050-7
Rights: © 1997 Elsevier Science B.V
Appears in Collections:Άρθρα/Articles

Show full item record

SCOPUSTM   
Citations 5

45
checked on Apr 24, 2017

WEB OF SCIENCETM
Citations 5

39
checked on Dec 17, 2016

Page view(s)

6
checked on Apr 28, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.