Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/3469
Title: | Unsupervised learning by examples: On-line versus off-line | Authors: | VAN DEN BROECK, Christian REIMANN, Peter |
Issue Date: | 1996 | Publisher: | AMERICAN PHYSICAL SOC | Source: | PHYSICAL REVIEW LETTERS, 76(12). p. 2188-2191 | Abstract: | We study both on-line and off-line unsupervised learning from p random patterns which are uniformly distributed on the N-sphere with the exception of a single symmetry breaking orientation B, along which they may be arbitrarily distributed. Supervised learning from the same kind of patterns is included as a special case. In the thermodynamic limit N --> infinity with alpha = p/N fixed we calculate the overlap R(alpha)= B . J/\J\\B\ between the unknown ''true'' B and the optimal ''Bayes'' hypothesis J with particular emphasis on the small and large cu asymptotics and the phenomenon of retarded learning. Finally, we identify a cost function whose minimum reproduces the off-line Bayes overlap. | Notes: | VandenBroeck, C, LIMBURGS UNIV CENTRUM,B-3590 DIEPENBEEK,BELGIUM. | Document URI: | http://hdl.handle.net/1942/3469 | DOI: | 10.1103/PhysRevLett.76.2188 | ISI #: | A1996TZ98400051 | Type: | Journal Contribution |
Appears in Collections: | Research publications |
Show full item record
SCOPUSTM
Citations
38
checked on Sep 2, 2020
WEB OF SCIENCETM
Citations
37
checked on Jul 18, 2024
Page view(s)
76
checked on Nov 7, 2023
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.