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
Source: 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.
Document URI: http://hdl.handle.net/1942/3493
DOI: 10.1088/0305-4470/29/13/021
ISI #: A1996UX09000021
Type: Journal Contribution
Appears in Collections:Research publications

Show full item record

SCOPUSTM   
Citations

26
checked on Sep 2, 2020

WEB OF SCIENCETM
Citations

22
checked on May 13, 2022

Page view(s)

42
checked on Feb 24, 2022

Google ScholarTM

Check

Altmetric


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