DC Field | Value | Language |
---|---|---|
dc.contributor.author | Oh, SH | ko |
dc.contributor.author | Lee, Soo-Young | ko |
dc.date.accessioned | 2013-03-02T22:09:42Z | - |
dc.date.available | 2013-03-02T22:09:42Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 1999-07 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON NEURAL NETWORKS, v.10, no.4, pp.960 - 964 | - |
dc.identifier.issn | 1045-9227 | - |
dc.identifier.uri | http://hdl.handle.net/10203/75792 | - |
dc.description.abstract | This letter proposes a:new error function at hidden layers to speed up the training of multilayer perceptrons (MLP's), With this new hidden error function, the layer-by-layer (LBL) algorithm approximately converges to the error backpropagation algorithm with optimum learning rates. Especially, the optimum learning rate for a hidden weight vector appears approximately as a multiplication of two optimum factors, one for minimizing the new hidden error function and the other for assigning hidden targets. Effectiveness of the proposed error function was: demonstrated for handwritten digit recognition and isolated-word recognition tasks. Very fast learning convergence as obtained for MLP's without the stalling problem experienced in conventional LBL algorithms. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | BACKPROPAGATION ALGORITHM | - |
dc.subject | LEARNING ALGORITHM | - |
dc.subject | NEURAL NETWORKS | - |
dc.subject | BY-LAYER | - |
dc.subject | CONVERGENCE | - |
dc.title | A new error function at hidden layers for fast training of multilayer perceptrons | - |
dc.type | Article | - |
dc.identifier.wosid | 000081385700024 | - |
dc.identifier.scopusid | 2-s2.0-0032678016 | - |
dc.type.rims | ART | - |
dc.citation.volume | 10 | - |
dc.citation.issue | 4 | - |
dc.citation.beginningpage | 960 | - |
dc.citation.endingpage | 964 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON NEURAL NETWORKS | - |
dc.contributor.localauthor | Lee, Soo-Young | - |
dc.contributor.nonIdAuthor | Oh, SH | - |
dc.type.journalArticle | Letter | - |
dc.subject.keywordAuthor | error function | - |
dc.subject.keywordAuthor | fast learning | - |
dc.subject.keywordAuthor | hidden nodes | - |
dc.subject.keywordAuthor | layer-by-layer algorithm | - |
dc.subject.keywordAuthor | optimum learning rates | - |
dc.subject.keywordPlus | BACKPROPAGATION ALGORITHM | - |
dc.subject.keywordPlus | LEARNING ALGORITHM | - |
dc.subject.keywordPlus | NEURAL NETWORKS | - |
dc.subject.keywordPlus | BY-LAYER | - |
dc.subject.keywordPlus | CONVERGENCE | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.