DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, S | - |
dc.date.accessioned | 2016-04-01T01:45:17Z | - |
dc.date.available | 2016-04-01T01:45:17Z | - |
dc.date.created | 2009-02-28 | - |
dc.date.issued | 2006-12 | - |
dc.identifier.issn | 0893-6080 | - |
dc.identifier.other | 2007-OAK-0000006503 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/23629 | - |
dc.description.abstract | Decorrelation and its higher-order generalization, independent component analysis (ICA), are fundamental and important tasks in unsupervised learning, that were studied mainly in the domain of Hebbian learning. In this paper we present a variation of the natural gradient ICA, differential ICA, where the learning relies on the concurrent change of output variables. We interpret the differential learning as the maximum likelihood estimation of parameters with latent variables represented by the random walk model. In such a framework, we derive the differential ICA algorithm and, in addition, we also present the differential decorrelation algorithm that is treated as a special instance of the differential ICA. Algorithm derivation and local stability analysis are given with some numerical experimental results. (c) 2006 Elsevier Ltd. All rights reserved. | - |
dc.description.statementofresponsibility | X | - |
dc.language | English | - |
dc.publisher | PERGAMON-ELSEVIER SCIENCE LTD | - |
dc.relation.isPartOf | NEURAL NETWORKS | - |
dc.subject | blind source separation | - |
dc.subject | decorrelation | - |
dc.subject | differential learning | - |
dc.subject | Hebbian learning | - |
dc.subject | independent component analysis | - |
dc.subject | BLIND SOURCE SEPARATION | - |
dc.subject | RECOGNITION | - |
dc.subject | REPRESENTATIONS | - |
dc.subject | FACES | - |
dc.title | Differential learning algorithms for decorrelation and independent component analysis | - |
dc.type | Article | - |
dc.contributor.college | 컴퓨터공학과 | - |
dc.identifier.doi | 10.1016/j.neunet.2006.06.002 | - |
dc.author.google | Choi, S | - |
dc.relation.volume | 19 | - |
dc.relation.issue | 10 | - |
dc.relation.startpage | 1558 | - |
dc.relation.lastpage | 1567 | - |
dc.contributor.id | 10077620 | - |
dc.relation.journal | NEURAL NETWORKS | - |
dc.relation.index | SCI급, SCOPUS 등재논문 | - |
dc.relation.sci | SCI | - |
dc.collections.name | Journal Papers | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | NEURAL NETWORKS, v.19, no.10, pp.1558 - 1567 | - |
dc.identifier.wosid | 000243215200010 | - |
dc.date.tcdate | 2019-01-01 | - |
dc.citation.endPage | 1567 | - |
dc.citation.number | 10 | - |
dc.citation.startPage | 1558 | - |
dc.citation.title | NEURAL NETWORKS | - |
dc.citation.volume | 19 | - |
dc.contributor.affiliatedAuthor | Choi, S | - |
dc.identifier.scopusid | 2-s2.0-33751206535 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.wostc | 6 | - |
dc.type.docType | Article | - |
dc.subject.keywordAuthor | blind source separation | - |
dc.subject.keywordAuthor | decorrelation | - |
dc.subject.keywordAuthor | differential learning | - |
dc.subject.keywordAuthor | Hebbian learning | - |
dc.subject.keywordAuthor | independent component analysis | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Neurosciences | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Neurosciences & Neurology | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.