Globally optimal parameters for on-line learning in multilayer neural networks


We present a framework for calculating globally optimal parameters, within a given time frame, for on-line learning in multilayer neural networks. We demonstrate the capability of this method by computing optimal learning rates in typical learning scenarios. A similar treatment allows one to determine the relevance of related training algorithms based on modifications to the basic gradient descent rule as well as to compare different training methods.

Divisions: College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: Copyright of the American Physical Society
Publication ISSN: 1079-7114
Last Modified: 29 Nov 2023 10:00
Date Deposited: 11 Mar 2019 17:28
Full Text Link: 10.1103/PhysRevLett.79.2578
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
http://prola.ap ... v79/i13/p2578_1 (Publisher URL)
PURE Output Type: Article
Published Date: 1997-09-29
Authors: Saad, David
Rattray, Magnus



Version: Accepted Version

| Preview

Export / Share Citation


Additional statistics for this record