Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/9055
Title: | Unsupervised learning by examples: On-line versus off-line | Authors: | VAN DEN BROECK, Christian | Issue Date: | 1998 | Publisher: | SPRINGER-VERLAG SINGAPORE PTE LTD | Source: | Wong, KYM. & King, I. & Yeung, DY. (Ed.) THEORETICAL ASPECTS OF NEURAL COMPUTATION - A MULTIDISCIPLINARY PERSPECTIVE. p. 249-255. | Abstract: | We study both on-line and off-line learning in the following unsupervised learning scheme: p patterns are sampled independently from a distribution on the N-sphere with a single symmetry breaking orientation. Exact results are obtained in the limit p --> infinity and N --> infinity with finite ratio p/N. One finds that for smooth pattern distributions, the asymptotic behavior of the optimal off-line and on-line learning are identical, and saturate the Cramer-Rao inequality from statistics. For discontinuous pattern distributions on the other hand, the optimal online algorithm needs (at least) twice as many examples asymptotically to reach the optimal off-line performance. | Notes: | Limburgs Univ Ctr, B-3590 Diepenbeek, Belgium. | Document URI: | http://hdl.handle.net/1942/9055 | ISI #: | 000078895600023 | Type: | Proceedings Paper | Validations: | ecoom 2000 |
Appears in Collections: | Research publications |
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.