Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/3529
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBOUTEN, Marcus-
dc.contributor.authorSCHIETSE, J-
dc.contributor.authorVAN DEN BROECK, Christian-
dc.date.accessioned2007-11-28T17:03:22Z-
dc.date.available2007-11-28T17:03:22Z-
dc.date.issued1995-
dc.identifier.citationPHYSICAL REVIEW E, 52(2). p. 1958-1967-
dc.identifier.issn1063-651X-
dc.identifier.urihttp://hdl.handle.net/1942/3529-
dc.description.abstractWe present a streamlined formalism which reduces the calculation of the generalization error for a perceptron, trained on random examples generated by a teacher perceptron, to a matter of simple algebra. The method is valid whenever the student perceptron can be identified as the unique minimum of a specific cost function. The asymptotic generalization error is calculated explicitly for a broad class of cost functions, and a specific cost function is singled out that leads to a generalization error extremely close to the one of the Bayes classifier.-
dc.language.isoen-
dc.publisherAMERICAN PHYSICAL SOC-
dc.titleGRADIENT DESCENT LEARNING IN PERCEPTRONS - A REVIEW OF ITS POSSIBILITIES-
dc.typeJournal Contribution-
dc.identifier.epage1967-
dc.identifier.issue2-
dc.identifier.spage1958-
dc.identifier.volume52-
local.format.pages10-
dc.description.notesBOUTEN, M, LIMBURGS UNIV CENTRUM,UNIV CAMPUS,B-3590 DIEPENBEEK,BELGIUM.-
local.type.refereedRefereed-
local.type.specifiedArticle-
dc.bibliographicCitation.oldjcatA1-
dc.identifier.doi10.1103/PhysRevE.52.1958-
dc.identifier.isiA1995RQ37700082-
item.contributorBOUTEN, Marcus-
item.contributorSCHIETSE, J-
item.contributorVAN DEN BROECK, Christian-
item.fulltextNo Fulltext-
item.fullcitationBOUTEN, Marcus; SCHIETSE, J & VAN DEN BROECK, Christian (1995) GRADIENT DESCENT LEARNING IN PERCEPTRONS - A REVIEW OF ITS POSSIBILITIES. In: PHYSICAL REVIEW E, 52(2). p. 1958-1967.-
item.accessRightsClosed Access-
Appears in Collections:Research publications
Show simple item record

Google ScholarTM

Check

Altmetric


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