Title
Gradient descent learning in perceptrons: a review of its possibilities Gradient descent learning in perceptrons: a review of its possibilities
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
52(1995) , p. 1958-1967
ISSN
1539-3755
1550-2376
ISI
A1995RQ37700082
Carrier
E
Target language
English (eng)
Full text (Publishers DOI)
Abstract
We present a streamlined formalism which reduces the calculation of the generalization error for a perceptron, trained on random examples generated by a teacher perceptron, to a matter of simple algebra. The method is valid whenever the student perceptron can be identified as the unique minimum of a specific cost function. The asymptotic generalization error is calculated explicitly for a broad class of cost functions, and a specific cost function is singled out that leads to a generalization error extremely close to the one of the Bayes classifier.
Full text (open access)
https://repository.uantwerpen.be/docman/irua/814dc8/8053.pdf
E-info
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:A1995RQ37700082&DestLinkType=RelatedRecords&DestApp=ALL_WOS&UsrCustomerID=ef845e08c439e550330acc77c7d2d848
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:A1995RQ37700082&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=ef845e08c439e550330acc77c7d2d848
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:A1995RQ37700082&DestLinkType=CitingArticles&DestApp=ALL_WOS&UsrCustomerID=ef845e08c439e550330acc77c7d2d848