Open Access System for Information Sharing

Login Library

 

Article
Cited 5 time in webofscience Cited 5 time in scopus
Metadata Downloads
Full metadata record
Files in This Item:
DC FieldValueLanguage
dc.contributor.authorXiong, YS-
dc.contributor.authorOh, JH-
dc.contributor.authorKwon, C-
dc.date.accessioned2015-06-25T03:10:59Z-
dc.date.available2015-06-25T03:10:59Z-
dc.date.created2009-02-28-
dc.date.issued1997-10-
dc.identifier.issn1063-651X-
dc.identifier.other2015-OAK-0000009947en_US
dc.identifier.urihttps://oasis.postech.ac.kr/handle/2014.oak/12339-
dc.description.abstractWe study the storage capacity of a fully connected committee machine with a large number K of hidden nodes. The storage capacity is obtained by analyzing the geometrical structure of the weight space related to the internal representation. By examining the asymptotic behavior of order parameters in the limit of large K, the storage capacity alpha(c) is found to be proportional to K root lnK up to the leading order. This result satisfies the mathematical bound given by Mitchison and Durbin [Biol. Cybern. 60, 345 (1989)], whereas the replica-symmetric solution in a conventional Gardner approach [Europhys. Lett. 41, 481 (1987); J. Phys. A 21, 257 (1988)] violates this bound.-
dc.description.statementofresponsibilityopenen_US
dc.languageEnglish-
dc.publisherAMERICAN PHYSICAL SOC-
dc.relation.isPartOfPHYSICAL REVIEW E-
dc.rightsBY_NC_NDen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/2.0/kren_US
dc.titleWeight space structure and the storage capacity of a fully connected committee machine-
dc.typeArticle-
dc.contributor.college기술경영 대학원 과정en_US
dc.identifier.doi10.1103/PhysRevE.56.4540-
dc.author.googleXIONG, YSen_US
dc.author.googleOH, JHen_US
dc.author.googleKWON, Cen_US
dc.relation.volume56en_US
dc.relation.issue4en_US
dc.relation.startpage4540en_US
dc.relation.lastpage4544en_US
dc.contributor.id10110134en_US
dc.relation.journalPHYSICAL REVIEW Een_US
dc.relation.indexSCI급, SCOPUS 등재논문en_US
dc.relation.sciSCIen_US
dc.collections.nameJournal Papersen_US
dc.type.rimsART-
dc.identifier.bibliographicCitationPHYSICAL REVIEW E, v.56, no.4, pp.4540 - 4544-
dc.identifier.wosidA1997YC32200101-
dc.date.tcdate2019-01-01-
dc.citation.endPage4544-
dc.citation.number4-
dc.citation.startPage4540-
dc.citation.titlePHYSICAL REVIEW E-
dc.citation.volume56-
dc.contributor.affiliatedAuthorOh, JH-
dc.identifier.scopusid2-s2.0-0007031169-
dc.description.journalClass1-
dc.description.journalClass1-
dc.description.wostc5-
dc.type.docTypeArticle-
dc.subject.keywordPlusMULTILAYER NEURAL NETWORKS-
dc.subject.keywordPlusINTERNAL REPRESENTATIONS-
dc.subject.keywordPlusMODELS-
dc.relation.journalWebOfScienceCategoryPhysics, Fluids & Plasmas-
dc.relation.journalWebOfScienceCategoryPhysics, Mathematical-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.relation.journalResearchAreaPhysics-

qr_code

  • mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher

오종훈OH, JONG HOON
Grad Program for Tech Innovation & Mgmt
Read more

Views & Downloads

Browse