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 Oct 14, 2024
Page view(s)
78
checked on Oct 30, 2023
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.