Title
Learning by examples from a non-uniform distribution Learning by examples from a non-uniform distribution
Author
Faculty/Department
Faculty of Sciences. Physics
Publication type
article
Publication
Melville, N.Y. :American Physical Society ,
Source (journal)
Physical review : E : statistical, nonlinear, and soft matter physics / American Physical Society. - Melville, N.Y., 2001 - 2015
Volume/pages
53(1996) , p. 3989-3998
ISSN
1539-3755
1550-2376
ISI
A1996UH48200042
Carrier
E
Target language
English (eng)
Full text (Publishers DOI)
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 αc=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.
Full text (open access)
https://repository.uantwerpen.be/docman/irua/fabd69/8070.pdf
E-info
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:A1996UH48200042&DestLinkType=RelatedRecords&DestApp=ALL_WOS&UsrCustomerID=ef845e08c439e550330acc77c7d2d848
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:A1996UH48200042&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=ef845e08c439e550330acc77c7d2d848
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:A1996UH48200042&DestLinkType=CitingArticles&DestApp=ALL_WOS&UsrCustomerID=ef845e08c439e550330acc77c7d2d848