www.uhasselt.be
DSpace

Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/3789

Title: NEAREST-NEIGHBOR CLASSIFIER FOR THE PERCEPTRON
Authors: BOUTEN, Marcus
VAN DEN BROECK, Christian
Issue Date: 1994
Publisher: EDITIONS PHYSIQUE
Citation: EUROPHYSICS LETTERS, 26(1). p. 69-74
Abstract: We 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.
Notes: BOUTEN, M, LIMBURGS UNIV CENTRUM,B-3610 DIEPENBEEK,BELGIUM.
URI: http://hdl.handle.net/1942/3789
ISI #: A1994NH19100012
ISSN: 0295-5075
Type: Journal Contribution
Appears in Collections: Research publications

Files in This Item:

There are no files associated with this item.

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