Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/2965
Title: Bayes-optimal performance in a discrete space
Authors: VAN DEN BROECK, Christian 
Copelli, M
Opper, M
Issue Date: 1999
Publisher: IOP PUBLISHING LTD
Source: JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 32(50). p. L555-L560
Abstract: We study a simple model of unsupervised learning where the single symmetry breaking vector has binary components +/-1. We calculate exactly the Bayes-optimal performance of an estimator which is required to lie in the same discrete space. We also show that, except for very special cases, such an estimator cannot be obtained by minimization of a class of variationally optimal potentials.
Notes: Limburgs Univ Ctr, B-3590 Diepenbeek, Belgium. Aston Univ, Neural Comp Res Grp, Birmingham B4 7ET, W Midlands, England.Copelli, M, Limburgs Univ Ctr, Univ Campus, B-3590 Diepenbeek, Belgium.
Document URI: http://hdl.handle.net/1942/2965
ISI #: 000084444100004
Type: Journal Contribution
Validations: ecoom 2001
Appears in Collections:Research publications

Show full item record

WEB OF SCIENCETM
Citations

3
checked on May 14, 2022

Page view(s)

46
checked on May 17, 2022

Google ScholarTM

Check


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