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/1942/3500

Title: Learning by examples from a nonuniform distribution
Authors: REIMANN, Peter
VAN DEN BROECK, Christian
Issue Date: 1996
Publisher: AMERICAN PHYSICAL SOC
Citation: PHYSICAL REVIEW E, 53(4). p. 3989-3998
Abstract: We present a general replica calculation for learning from examples generated by a nonuniform pattern distribution with a single symmetry-breaking orientation. Our results cover the three main learning scenarios: storage of patterns with random classifications by a perceptron, supervised learning from a teacher, and unsupervised learning. We show that for a perceptron the critical storage capacity alpha(c) = 2 is completely independent of the pattern distribution provided it is point symmetric or provided the classification as +/-1 is unbiased. In a particular model for supervised learning we find that an ideal (Bayes) student learns most from a few examples if they are easy and from a large number if they are difficult. Learning based on the minimization of a specific class of (quadratic) cost functions is solved completely for all three scenarios.
Notes: LIMBURGS UNIV CENTRUM,B-3590 DIEPENBEEK,BELGIUM.
URI: http://hdl.handle.net/1942/3500
DOI: 10.1103/PhysRevE.53.3989
ISI #: A1996UH48200042
ISSN: 1063-651X
Type: Journal Contribution
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.