Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/3757
Title: GENERALIZATION ERROR IN A SELF-SIMILAR COMMITTEE MACHINE
Authors: VAN DEN BROECK, Christian 
PARRONDO, JMR
Issue Date: 1993
Publisher: AMERICAN PHYSICAL SOC
Source: PHYSICAL REVIEW LETTERS, 71(15). p. 2355-2359
Abstract: We derive the form and properties of the generalization error for a self-similar feedforward network (constructed through an iterative procedure of test set partitioning combined with majority voting). We discuss the universality of these results and conjecture that the generalization error rate epsilon(alpha) as a function of the amount of training alpha never decreases faster than epsilon(alpha) - 1/2 is similar to square-root alpha in the limit alpha --> 0. We show how the self-similar architecture can be used to improve the generalization performance.
Notes: LIMBURGS UNIV CENTRUM,B-3590 DIEPENBEEK,BELGIUM. UNIV COMPLUTENSE MADRID,DEPT FIS APLICADA 1,E-28040 MADRID,SPAIN.VANDENBROECK, C, UNIV CALIF SAN DIEGO,DEPT CHEM,0340,LA JOLLA,CA 92093.
Document URI: http://hdl.handle.net/1942/3757
ISI #: A1993MA96200001
Type: Journal Contribution
Appears in Collections:Research publications

Show full item record

WEB OF SCIENCETM
Citations

4
checked on May 14, 2022

Page view(s)

46
checked on May 18, 2022

Google ScholarTM

Check


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