Globally optimal on-line learning rules

Abstract

We present a method for determining the globally optimal on-line learning rule for a soft committee machine under a statistical mechanics framework. This work complements previous results on locally optimal rules, where only the rate of change in generalization error was considered. We maximize the total reduction in generalization error over the whole learning process and show how the resulting rule can significantly outperform the locally optimal rule.

Divisions: College of Engineering & Physical Sciences > School of Informatics and Digital Engineering > Mathematics
College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: Copyright of the Massachusetts Institute of Technology Press (MIT Press)
Uncontrolled Keywords: on-line learning,statistical mechanics,generalization error,optimal rule,resulting rule
Publication ISSN: 1049-5258
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
http://mitpress ... type=2&tid=8363 (Publisher URL)
PURE Output Type: Article
Published Date: 1998-01
Authors: Rattray, Magnus
Saad, David (ORCID Profile 0000-0001-9821-2623)

Download

[img]

Version: Published Version

| Preview

Export / Share Citation


Statistics

Additional statistics for this record