Neural Comp. NEW Faster Access
HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
QUICK SEARCH:   [advanced]


     

This Article
Right arrow Full Text
Right arrow Full Text (PDF)
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Similar articles in this journal
Right arrow Similar articles in PubMed
Right arrow Alert me to new issues of the journal
Right arrow Download to citation manager
Right arrow reprints & permissions
Citing Articles
Right arrow Citing Articles via Google Scholar
Google Scholar
Right arrow Articles by Navia-Vázquez, A.
Right arrow Articles by Figueiras-Vidal, A. R.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by Navia-Vázquez, A.
Right arrow Articles by Figueiras-Vidal, A. R.
(Neural Computation. 2000;12:1429-1447.)
© 2000 The MIT Press

Letter

Efficient Block Training of Multilayer Perceptrons

A. Navia-Vázquez

DTC, Universidad Carlos III de Madrid, 28911-Leganés (Madrid), Spain

A. R. Figueiras-Vidal

DTC, Universidad Carlos III de Madrid, 28911-Leganés (Madrid), Spain

The attractive possibility of applying layerwise block training algorithms to multilayer perceptrons MLP, which offers initial advantages in computational effort, is refined in this article by means of introducing a sensitivity correction factor in the formulation. This results in a clear performance advantage, which we verify in several applications. The reasons for this advantage are discussed and related to implicit relations with second-order techniques, natural gradient formulations through Fisher's information matrix, and sample selection. Extensions to recurrent networks and other research lines are suggested at the close of the article.






HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
J COGNITIVE NEUROSCIENCE NEURAL COMPUTATION MIT PRESS JOURNALS
Copyright © 2000 by The MIT Press.