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/1942/3493

Title: A Gaussian scenario for unsupervised learning
Authors: REIMANN, Peter
VAN DEN BROECK, Christian
BEX, Geert Jan
Issue Date: 1996
Publisher: IOP PUBLISHING LTD
Citation: JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 29(13). p. 3521-3535
Abstract: We consider random patterns on the N-sphere which are uniformly distributed with the exception of a single symmetry-breaking orientation, along which they are Gaussian distributed. The unsupervised recognition of this orientation by different learning rules is studied in the large-N limit using the replica method. The model is simple enough to be analytically tractable and rich enough to exhibit most of the phenomena observed with other pattern distributions. A learning algorithm based on the minimization of a cost function is identified which reaches the upper theoretical limit imposed by the optimal (Bayes-) learning scenario. An implementation of this algorithm is proposed and tested numerically.
Notes: LIMBURGS UNIV CENTRUM,B-3590 DIEPENBEEK,BELGIUM.Reimann, P, LORAND EOTVOS UNIV,PUSKIN U 5-7,H-1088 BUDAPEST,HUNGARY.
URI: http://hdl.handle.net/1942/3493
DOI: 10.1088/0305-4470/29/13/021
ISI #: A1996UX09000021
ISSN: 0305-4470
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.