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 Jul 13, 2024
Page view(s)
76
checked on Nov 7, 2023
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.