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 Alert me to new issues of the journal
Right arrow Download to citation manager
Right arrow reprints & permissions
Google Scholar
Right arrow Articles by Sutskever, I.
Right arrow Articles by Hinton, G. E.
PubMed
Right arrow Articles by Sutskever, I.
Right arrow Articles by Hinton, G. E.
(Neural Computation. 2008;20:2629-2636.)
© 2008 The MIT Press

Note

Deep, Narrow Sigmoid Belief Networks Are Universal Approximators

Ilya Sutskever

ilya{at}cs.utoronto.ca Department of Computer Science, University of Toronto, Toronto, Ontario M55 3G4, Canada

Geoffrey E. Hinton

hinton{at}cs.utoronto.ca Department of Computer Science, University of Toronto, Toronto, Ontario M55 3G4, Canada

In this note, we show that exponentially deep belief networks can approximate any distribution over binary vectors to arbitrary accuracy, even when the width of each layer is limited to the dimensionality of the data. We further show that such networks can be greedily learned in an easy yet impractical way.






HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
J COGNITIVE NEUROSCIENCE NEURAL COMPUTATION MIT PRESS JOURNALS
Copyright © 2008 by The MIT Press.