GLOBALLY OPTIMAL PARAMETERS FOR ONLINE LEARNING IN MULTILAYER NEURAL NETWORKS

Authors
Citation
D. Saad et M. Rattray, GLOBALLY OPTIMAL PARAMETERS FOR ONLINE LEARNING IN MULTILAYER NEURAL NETWORKS, Physical review letters, 79(13), 1997, pp. 2578-2581
Citations number
10
Categorie Soggetti
Physics
Journal title
ISSN journal
00319007
Volume
79
Issue
13
Year of publication
1997
Pages
2578 - 2581
Database
ISI
SICI code
0031-9007(1997)79:13<2578:GOPFOL>2.0.ZU;2-A
Abstract
We present a framework for calculating globally optimal parameters, wi thin a given time frame, for on-line learning in multilayer neural net works. We demonstrate the capability of this method by computing optim al learning rates in typical learning scenarios. A similar treatment a llows one to determine the relevance of related training algorithms ba sed on modifications to the basic gradient descent rule as well as to compare different training methods.