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 | Source: | 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. | Document URI: | http://hdl.handle.net/1942/3789 | ISI #: | A1994NH19100012 | Type: | Journal Contribution |
Appears in Collections: | Research publications |
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.