DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Cheol-Taek | ko |
dc.contributor.author | Lee, Ju-Jang | ko |
dc.date.accessioned | 2013-03-07T17:09:33Z | - |
dc.date.available | 2013-03-07T17:09:33Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2008-02 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON NEURAL NETWORKS, v.19, pp.371 - 375 | - |
dc.identifier.issn | 1045-9227 | - |
dc.identifier.uri | http://hdl.handle.net/10203/90748 | - |
dc.description.abstract | The variable projection (VP) method for separable nonlinear least squares.(SNLLS) is presented and incorporated into the Levenberg-Marquardt optimization algorithm for training two-layered feedforward neural networks. It is shown that the Jacobian of variable projected networks can be computed by simple modification of the back-propagation algorithm. The suggested algorithm is efficient compared to conventional techniques such as conventional Levenberg-Marquardt algorithm (LMA), hybrid gradient algorithm (HGA), and extreme learning machine (ELM). | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | NONLINEAR LEAST-SQUARES | - |
dc.subject | MARQUARDT ALGORITHM | - |
dc.title | Training two-layered feedforward networks with variable projection method | - |
dc.type | Article | - |
dc.identifier.wosid | 000253272100017 | - |
dc.identifier.scopusid | 2-s2.0-40549088280 | - |
dc.type.rims | ART | - |
dc.citation.volume | 19 | - |
dc.citation.beginningpage | 371 | - |
dc.citation.endingpage | 375 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON NEURAL NETWORKS | - |
dc.identifier.doi | 10.1109/TNN.2007.911739 | - |
dc.contributor.localauthor | Lee, Ju-Jang | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | feedforward neural networks | - |
dc.subject.keywordAuthor | Levenberg-Marquardt algorithm (LMA) | - |
dc.subject.keywordAuthor | separable nonlinear least squares (SNLLS) | - |
dc.subject.keywordAuthor | variable projection (VP) method | - |
dc.subject.keywordPlus | NONLINEAR LEAST-SQUARES | - |
dc.subject.keywordPlus | MARQUARDT ALGORITHM | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.