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/1942/3529

Title: GRADIENT DESCENT LEARNING IN PERCEPTRONS - A REVIEW OF ITS POSSIBILITIES
Authors: BOUTEN, Marcus
SCHIETSE, J
VAN DEN BROECK, Christian
Issue Date: 1995
Publisher: AMERICAN PHYSICAL SOC
Citation: PHYSICAL REVIEW E, 52(2). p. 1958-1967
Abstract: We 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.
Notes: BOUTEN, M, LIMBURGS UNIV CENTRUM,UNIV CAMPUS,B-3590 DIEPENBEEK,BELGIUM.
URI: http://hdl.handle.net/1942/3529
DOI: 10.1103/PhysRevE.52.1958
ISI #: A1995RQ37700082
ISSN: 1063-651X
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.