Document Server@UHasselt >
Research publications >
Please use this identifier to cite or link to this item:
|Title: ||GENERALIZATION ERROR IN A SELF-SIMILAR COMMITTEE MACHINE|
|Authors: ||VAN DEN BROECK, Christian|
|Issue Date: ||1993|
|Publisher: ||AMERICAN PHYSICAL SOC|
|Citation: ||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.|
|ISI #: ||A1993MA96200001|
|Type: ||Journal Contribution|
|Appears in Collections: ||Research publications|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.