Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/3670
Title: SYSTEMS THAT CAN LEARN FROM EXAMPLES - REPLICA CALCULATION OF UNIFORM-CONVERGENCE BOUNDS FOR PERCEPTRONS
Authors: ENGEL, A
VAN DEN BROECK, Christian 
Issue Date: 1993
Publisher: AMERICAN PHYSICAL SOC
Source: PHYSICAL REVIEW LETTERS, 71(11). p. 1772-1775
Abstract: The generalization abilities of neural networks for inferring a rule on the basis of examples can be characterized by the convergence of the learning error to the generalization error with increasing size of the training set. Using the replica technique, we calculate the maximum difference between training and generalization error for the ensemble of all perceptrons trained by a teacher perceptron and the maximal generalization error for the perceptrons that have a training error equal to zero. The results axe compared with the rigorous bounds provided by the Vapnik-Chervonenkis theorem.
Notes: LIMBURGS UNIV CENTRUM,B-3590 DIEPENBEEK,BELGIUM.ENGEL, A, GEORG AUGUST UNIV,INST THEORET PHYS,D-37073 GOTTINGEN,GERMANY.
Document URI: http://hdl.handle.net/1942/3670
ISI #: A1993LX11900029
Type: Journal Contribution
Appears in Collections:Research publications

Show full item record

WEB OF SCIENCETM
Citations

11
checked on May 22, 2022

Page view(s)

52
checked on May 20, 2022

Google ScholarTM

Check


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