Please use this identifier to cite or link to this item: https://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
Category: Electrical Engineering - Electronic Engineering - Information Engineering
Field: Engineering and Technology
Issue Date: Nov-1997
Publisher: Elsevier
Source: Neurocomputing, 1997, vol. 17, no. 3-4, pp. 167-194
Journal: Neurocomputing 
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.
ISSN: 0925-2312
DOI: 10.1016/S0925-2312(97)00050-7
Rights: © 1997 Elsevier Science B.V
Type: Article
Appears in Collections:Άρθρα/Articles

Show full item record

SCOPUSTM   
Citations 50

46
checked on Feb 13, 2018

WEB OF SCIENCETM
Citations

40
checked on Aug 13, 2019

Page view(s)

69
Last Week
1
Last month
5
checked on Aug 17, 2019

Google ScholarTM

Check

Altmetric


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