Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/3057
Τίτλος: | Coupling weight elimination and genetic algorithms | Συγγραφείς: | Kasparis, Takis Bebis, George N. Georgiopoulos, Michael N. |
metadata.dc.contributor.other: | Κασπαρής, Τάκης | Major Field of Science: | Engineering and Technology | Field Category: | Electrical Engineering - Electronic Engineering - Information Engineering | Λέξεις-κλειδιά: | Functions;Genetic algorithms;Neural networks;Computer networks | Ημερομηνία Έκδοσης: | Ιου-1996 | Πηγή: | IEEE International Conference on Neural Networks, 1996, vol. 2, pp. 1115-1120 | Conference: | IEEE International Conference on Neural Networks | Περίληψη: | Network size plays an important role in the generalization performance of a network. A number of approaches which try to determine an 'appropriate' network size for a given problem have been developed during the last few years. Although it is usually demonstrated that such approaches are capable of finding small size networks that solve the problem at hand, it is quite remarkable that the generalization capabilities of these networks have not been thoroughly explored. In this paper, we have considered the weight elimination technique and we propose a scheme where it is coupled with genetic algorithms. Our objective is not only to find smaller size networks that solve the problem at hand, by pruning larger size networks, but also to improve generalization. The innovation of our work relies on a fitness function which uses an adaptive parameter to encourage the reproduction of networks having good generalization performance and a relatively small size. | ISBN: | 0-7803-3210-5 | DOI: | 10.1109/ICNN.1996.549054 | Rights: | © 1996 IEEE | Type: | Conference Papers | Affiliation: | University of Central Florida | Affiliation: | University of Central Florida | Publication Type: | Peer Reviewed |
Εμφανίζεται στις συλλογές: | Κεφάλαια βιβλίων/Book chapters |
CORE Recommender
Page view(s) 20
444
Last Week
1
1
Last month
28
28
checked on 13 Μαρ 2025
Google ScholarTM
Check
Altmetric
Όλα τα τεκμήρια του δικτυακού τόπου προστατεύονται από πνευματικά δικαιώματα