Repository logo
 
Publication

A hybrid training method for B-spline neural networks

dc.contributor.authorCabrita, Cristiano Lourenço
dc.contributor.authorBotzheim, J.pt_PT
dc.contributor.authorRuano, Antonio
dc.contributor.authorKóczy, László T.pt_PT
dc.date.accessioned2009-02-13T17:09:29Z
dc.date.available2009-02-13T17:09:29Z
dc.date.issued2008
dc.description.abstractCurrent and past research has brought up new views related to the optimization of neural networks. For a fixed structure, second order methods are seen as the most promising. From previous works we have shown how second order methods are of easy applicability to a neural network. Namely, we have proved how the Levenberg-Marquard possesses not only better convergence but how it can assure the convergence to a local minima. However, as any gradient-based method, the results obtained depend on the startup point. In this work, a reformulated Evolutionary algorithm - the Bacterial Programming for Levenberg-Marquardt is proposed, as an heuristic which can be used to determine the most suitable starting points, therefore achieving, in most cases, the global optimum.pt_PT
dc.formatapplication/pdfpt_PT
dc.identifier.citationIEEE International Workshop on Intelligent Signal Processing (WISP). - Faro, 1-3 September 2005. - p. 165-170pt_PT
dc.identifier.otherAUT: ARU00698; CCA01443;
dc.identifier.urihttp://hdl.handle.net/10400.1/87
dc.language.isoporpt_PT
dc.publisherFaropt_PT
dc.relation.urihttp://www.bib.ualg.pt/artigos/DocentesEST/CABHyb.pdfpt_PT
dc.rights.urirestrictedAccessen
dc.subjectAlgoritmo de levenberg-marquardpt_PT
dc.subjectAlgoritmo bacterianopt_PT
dc.subjectProgramação genéticapt_PT
dc.subjectB-splinespt_PT
dc.titleA hybrid training method for B-spline neural networkspt_PT
dc.typejournal article
dspace.entity.typePublication
person.familyNameCabrita
person.familyNameRuano
person.givenNameCristiano Lourenço
person.givenNameAntonio
person.identifier.ciencia-idFF1E-13A0-A269
person.identifier.orcid0000-0003-4946-0465
person.identifier.orcid0000-0002-6308-8666
person.identifier.ridB-4135-2008
person.identifier.scopus-author-id55958626100
person.identifier.scopus-author-id7004284159
rcaap.typearticlept_PT
relation.isAuthorOfPublication081b091f-c9fa-470a-9a28-51fe4c85864a
relation.isAuthorOfPublication13813664-b68b-40aa-97a9-91481a31ebf2
relation.isAuthorOfPublication.latestForDiscovery13813664-b68b-40aa-97a9-91481a31ebf2

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
CABHyb.pdf
Size:
434.36 KB
Format:
Adobe Portable Document Format