Neural Comp. Sign up for ETOCS
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 Kärkkäinen, T.
Right arrow Articles by Heikkola, E.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by Kärkkäinen, T.
Right arrow Articles by Heikkola, E.
(Neural Computation. 2004;16:837-862.)
© 2004 The MIT Press

Letter

Robust Formulations for Training Multilayer Perceptrons

Tommi Kärkkäinen

tka{at}mit.jyu.fi, Department of Mathematical Information Technology, University of Jyväskylä, FIN-40014 University of Jyväskylä, Finland

Erkki Heikkola

emsh{at}mit.jyu.fi, Department of Mathematical Information Technology, University of Jyväskylä, FIN-40014 University of Jyväskylä, Finland

The connection between robust statistical estimates and nonsmooth optimization is established. Based on the resulting family of optimization problems, robust learning problem formulations with regularization-based control on the model complexity of the multilayer perceptron network are described and analyzed. Numerical experiments for simulated regression problems are conducted, and new strategies for determining the regularization coefficient are proposed and evaluated.






HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
J COGNITIVE NEUROSCIENCE NEURAL COMPUTATION MIT PRESS JOURNALS
Copyright © 2004 by The MIT Press.