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
Source: 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.
Document URI: http://hdl.handle.net/1942/3500
DOI: 10.1103/PhysRevE.53.3989
ISI #: A1996UH48200042
Type: Journal Contribution
Appears in Collections:Research publications

Show full item record

SCOPUSTM   
Citations

22
checked on Sep 2, 2020

WEB OF SCIENCETM
Citations

21
checked on May 21, 2022

Page view(s)

58
checked on May 20, 2022

Google ScholarTM

Check

Altmetric


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