www.uhasselt.be
DSpace

Document Server@UHasselt >
Research >
Research publications >

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
Citation: 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.
URI: http://hdl.handle.net/1942/9055
ISI #: 000078895600023
Type: Proceedings Paper
Validation: ecoom, 2000
Appears in Collections: Research publications

Files in This Item:

There are no files associated with this item.

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