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 de Angulo, V. R.
Right arrow Articles by Torras, C.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by de Angulo, V. R.
Right arrow Articles by Torras, C.
(Neural Computation. 2001;13:1119-1135.)
© 2001 The MIT Press

Letter

Architecture-Independent Approximation of Functions

Vicente Ruiz de Angulo

Institut de Robòtica i Informàtica Industrial, (CSIC-UPC), 08034-Barcelona, Spain

Carme Torras

Institut de Robòtica i Informàtica Industrial, (CSIC-UPC), 08034-Barcelona, Spain

We show that minimizing the expected error of a feedforward network over a distribution of weights results in an approximation that tends to be independent of network size as the number of hidden units grows. This minimization can be easily performed, and the complexity of the resulting function implemented by the network is regulated by the variance of the weight distribution. For a fixed variance, there is a number of hidden units above which either the implemented function does not change or the change is slight and tends to zero as the size of the network grows. In sum, the control of the complexity depends on only the variance, not the architecture, provided it is large enough.






HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
J COGNITIVE NEUROSCIENCE NEURAL COMPUTATION MIT PRESS JOURNALS
Copyright © 2001 by The MIT Press.