DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ahn, JH | - |
dc.contributor.author | Oh, JH | - |
dc.contributor.author | Choi, S | - |
dc.date.accessioned | 2016-04-01T01:40:46Z | - |
dc.date.available | 2016-04-01T01:40:46Z | - |
dc.date.created | 2009-02-28 | - |
dc.date.issued | 2007-03 | - |
dc.identifier.issn | 0925-2312 | - |
dc.identifier.other | 2007-OAK-0000006742 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/23464 | - |
dc.description.abstract | A common derivation of principal component analysis (PCA) is based on the minimization of the squared-error between centered data and linear model, corresponding to the reconstruction error. In fact, minimizing the squared-error leads to principal subspace analysis where scaled and rotated principal axes of a set of observed data, are estimated. In this paper, we introduce and investigate an alternative error measure, integrated-squared error (ISE), the minimization of which determines the exact principal axes (without rotational ambiguity) of a set of observed data. We show that exact principal directions emerge from the minimization of ISE. We present a simple EM algorithm, 'EM-ePCA', which is similar to EM-PCA [S.T. Roweis, EM algorithms for PCA and SPCA, in: Advances in Neural Information Processing Systems, vol. 10, MIT Press, Cambridge, 1998, pp. 626-632.], but finds exact principal directions without rotational ambiguity. In addition, we revisit the generalized Hebbian algorithm (GHA) and show that it emerges from the ISE minimization in a single-layer linear feedforward neural network. (c) 2006 Elsevier B.V. All rights reserved. | - |
dc.description.statementofresponsibility | X | - |
dc.language | English | - |
dc.publisher | ELSEVIER SCIENCE BV | - |
dc.relation.isPartOf | NEUROCOMPUTING | - |
dc.subject | EM algorithm | - |
dc.subject | generalized Hebbian algorithm | - |
dc.subject | generative models | - |
dc.subject | probabilistic coupled models | - |
dc.subject | separable LS | - |
dc.subject | PCA | - |
dc.subject | COMPONENT ANALYSIS | - |
dc.title | Learning principal directions: Integrated-squared-error minimization | - |
dc.type | Article | - |
dc.contributor.college | 컴퓨터공학과 | - |
dc.identifier.doi | 10.1016/j.neucom.2006.06.004 | - |
dc.author.google | Ahn, JH | - |
dc.author.google | Oh, JH | - |
dc.author.google | Choi, S | - |
dc.relation.volume | 70 | - |
dc.relation.issue | 40003 | - |
dc.relation.startpage | 1372 | - |
dc.relation.lastpage | 1381 | - |
dc.contributor.id | 10077620 | - |
dc.relation.journal | NEUROCOMPUTING | - |
dc.relation.index | SCI급, SCOPUS 등재논문 | - |
dc.relation.sci | SCI | - |
dc.collections.name | Journal Papers | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | NEUROCOMPUTING, v.70, no.40003, pp.1372 - 1381 | - |
dc.identifier.wosid | 000245581600024 | - |
dc.date.tcdate | 2019-01-01 | - |
dc.citation.endPage | 1381 | - |
dc.citation.number | 40003 | - |
dc.citation.startPage | 1372 | - |
dc.citation.title | NEUROCOMPUTING | - |
dc.citation.volume | 70 | - |
dc.contributor.affiliatedAuthor | Oh, JH | - |
dc.contributor.affiliatedAuthor | Choi, S | - |
dc.identifier.scopusid | 2-s2.0-33847380221 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.wostc | 5 | - |
dc.type.docType | Article | - |
dc.subject.keywordAuthor | EM algorithm | - |
dc.subject.keywordAuthor | generalized Hebbian algorithm | - |
dc.subject.keywordAuthor | generative models | - |
dc.subject.keywordAuthor | probabilistic coupled models | - |
dc.subject.keywordAuthor | separable LS | - |
dc.subject.keywordAuthor | PCA | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
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.