A selective learning method to improve the generalization of multilayer feedforward neural networks.

e-Archivo Repository

Show simple item record

dc.contributor.author Galván, Inés M.
dc.contributor.author Isasi, Pedro
dc.contributor.author Aler, Ricardo
dc.contributor.author Valls, José M.
dc.date.accessioned 2009-04-30T12:18:30Z
dc.date.available 2009-04-30T12:18:30Z
dc.date.issued 2001-04
dc.identifier.bibliographicCitation International Journal of Neural Systems, 2001, vol. 11, n. 2, p. 167-177
dc.identifier.issn 0129-0657
dc.identifier.uri http://hdl.handle.net/10016/4093
dc.description.abstract Multilayer feedforward neural networks with backpropagation algorithm have been used successfully in many applications. However, the level of generalization is heavily dependent on the quality of the training data. That is, some of the training patterns can be redundant or irrelevant. It has been shown that with careful dynamic selection of training patterns, better generalization performance may be obtained. Nevertheless, generalization is carried out independently of the novel patterns to be approximated. In this paper, we present a learning method that automatically selects the training patterns more appropriate to the new sample to be predicted. This training method follows a lazy learning strategy, in the sense that it builds approximations centered around the novel sample. The proposed method has been applied to three different domains: two artificial approximation problems and a real time series prediction problem. Results have been compared to standard backpropagation using the complete training data set and the new method shows better generalization abilities.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher World Scientific Publishing Company
dc.rights © World Scientific Publishing Company
dc.subject.classification Neural networks (Computer science)
dc.subject.classification Feedforward control systems
dc.subject.classification Sefl-organizing systems
dc.title A selective learning method to improve the generalization of multilayer feedforward neural networks.
dc.type article
dc.type.review PeerReviewed
dc.description.status Publicado
dc.relation.publisherversion http://web.ebscohost.com/ehost/detail?vid=1&hid=102&sid=329db7e0-5da7-4c17-9ed5-b718b41ea578%40sessionmgr102&bdata=JnNpdGU9ZWhvc3QtbGl2ZQ%3d%3d#db=aph&AN=7084469
dc.subject.eciencia Informática
dc.rights.accessRights openAccess
dc.identifier.publicationfirstpage 167
dc.identifier.publicationissue 2
dc.identifier.publicationtitle International Journal of Neural Systems
dc.identifier.publicationvolume 11
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

This item appears in the following Collection(s)

Show simple item record