Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/3789
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBOUTEN, Marcus-
dc.contributor.authorVAN DEN BROECK, Christian-
dc.date.accessioned2007-11-29T13:39:14Z-
dc.date.available2007-11-29T13:39:14Z-
dc.date.issued1994-
dc.identifier.citationEUROPHYSICS LETTERS, 26(1). p. 69-74-
dc.identifier.issn0295-5075-
dc.identifier.urihttp://hdl.handle.net/1942/3789-
dc.description.abstractWe calculate the generalization error for the nearest-neighbour classifier based on a set of random examples generated by a teacher perceptron. Explicit results are given for dimensions N = 2, N = 3 and N --> infinity. For a natural extension of the nearest-neighbour rule which includes the k-nearest-neighbour rule and the Hebbian perceptron as particular cases it is found that the Hebbian perceptron gives the smallest generalization error.-
dc.language.isoen-
dc.publisherEDITIONS PHYSIQUE-
dc.titleNearest-neighbor classifier for the perceptron-
dc.typeJournal Contribution-
dc.identifier.epage74-
dc.identifier.issue1-
dc.identifier.spage69-
dc.identifier.volume26-
local.format.pages6-
dc.description.notesBOUTEN, M, LIMBURGS UNIV CENTRUM,B-3610 DIEPENBEEK,BELGIUM.-
local.type.refereedRefereed-
local.type.specifiedArticle-
dc.bibliographicCitation.oldjcatA1-
dc.identifier.isiA1994NH19100012-
item.contributorBOUTEN, Marcus-
item.contributorVAN DEN BROECK, Christian-
item.fullcitationBOUTEN, Marcus & VAN DEN BROECK, Christian (1994) Nearest-neighbor classifier for the perceptron. In: EUROPHYSICS LETTERS, 26(1). p. 69-74.-
item.accessRightsClosed Access-
item.fulltextNo Fulltext-
Appears in Collections:Research publications
Show simple item record

Google ScholarTM

Check


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