Show simple item record

dc.contributor.authorPan, Z.
dc.contributor.authorSabisch, T.
dc.contributor.authorAdams, R.G.
dc.contributor.authorBolouri, H.
dc.date.accessioned2008-02-05T12:23:19Z
dc.date.available2008-02-05T12:23:19Z
dc.date.issued1999
dc.identifier.citationPan , Z , Sabisch , T , Adams , R G & Bolouri , H 1999 , Staged training of Neocognitron by evolutionary algorithms . in In: Procs of the 1999 Congress on Evolutionary Computation (CEC'99) Vol. 3 . IEEE , pp. 1965-1972 . https://doi.org/10.1109/CEC.1999.785515
dc.identifier.isbn0780355369
dc.identifier.otherPURE: 101323
dc.identifier.otherPURE UUID: e460cbc8-3656-4f2d-b624-b42018a580d6
dc.identifier.otherdspace: 2299/1569
dc.identifier.otherScopus: 20444408205
dc.identifier.urihttp://hdl.handle.net/2299/1569
dc.description.abstractThe Neocognitron, inspired by the mammalian visual system, is a complex neural network with numerous parameters and weights which should be trained in order to utilise it for pattern recognition. However, it is not easy to optimise these parameters and weights by gradient decent algorithms. In this paper, we present a staged training approach using evolutionary algorithms. The experiments demonstrate that evolutionary algorithms can successfully train the Neocognitron to perform image recognition on real world problems.en
dc.language.isoeng
dc.publisherIEEE
dc.relation.ispartofIn: Procs of the 1999 Congress on Evolutionary Computation (CEC'99) Vol. 3
dc.rightsOpen
dc.titleStaged training of Neocognitron by evolutionary algorithmsen
dc.contributor.institutionSchool of Computer Science
dc.relation.schoolSchool of Computer Science
dcterms.dateAccepted1999
rioxxterms.versionofrecordhttps://doi.org/10.1109/CEC.1999.785515
rioxxterms.typeOther
herts.preservation.rarelyaccessedtrue
herts.rights.accesstypeOpen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record