Sciweavers

NECO
2008

Deep, Narrow Sigmoid Belief Networks Are Universal Approximators

13 years 9 months ago
Deep, Narrow Sigmoid Belief Networks Are Universal Approximators
In this paper we show that exponentially deep belief networks [3, 7, 4] 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. This resolves an open the problem in [6]. We further show that such networks can be greedily learned in an easy yet impractical way.
Ilya Sutskever, Geoffrey E. Hinton
Added 14 Dec 2010
Updated 14 Dec 2010
Type Journal
Year 2008
Where NECO
Authors Ilya Sutskever, Geoffrey E. Hinton
Comments (0)