Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/3529
Title: | GRADIENT DESCENT LEARNING IN PERCEPTRONS - A REVIEW OF ITS POSSIBILITIES | Authors: | BOUTEN, Marcus SCHIETSE, J VAN DEN BROECK, Christian |
Issue Date: | 1995 | Publisher: | AMERICAN PHYSICAL SOC | Source: | PHYSICAL REVIEW E, 52(2). p. 1958-1967 | 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. | Notes: | BOUTEN, M, LIMBURGS UNIV CENTRUM,UNIV CAMPUS,B-3590 DIEPENBEEK,BELGIUM. | Document URI: | http://hdl.handle.net/1942/3529 | DOI: | 10.1103/PhysRevE.52.1958 | ISI #: | A1995RQ37700082 | Type: | Journal Contribution |
Appears in Collections: | Research publications |
Show full item record
SCOPUSTM
Citations
23
checked on Sep 2, 2020
WEB OF SCIENCETM
Citations
24
checked on Jul 18, 2024
Page view(s)
78
checked on Nov 7, 2023
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.