Format

Send to

Choose Destination
Neural Comput. 2008 Nov;20(11):2629-36. doi: 10.1162/neco.2008.12-07-661.

Deep, narrow sigmoid belief networks are universal approximators.

Author information

1
Department of Computer Science, University of Toronto, Toronto, Ontario M55 3G4, Canada. ilya@cs.utoronto.ca

Abstract

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.

PMID:
18533819
DOI:
10.1162/neco.2008.12-07-661
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Atypon
Loading ...
Support Center