Sciweavers

NECO
2008
146views more  NECO 2008»
13 years 4 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 lay...
Ilya Sutskever, Geoffrey E. Hinton
SIROCCO
2007
13 years 6 months ago
Optimal Conclusive Sets for Comparator Networks
A set of input vectors S is conclusive if correct functionality for all input vectors is implied by correct functionality over vectors in S. We consider four functionalities of co...
Guy Even, Tamir Levi, Ami Litman