3 search results - page 1 / 1 » Deep, Narrow Sigmoid Belief Networks Are Universal Approxima... |
NECO
2008
13 years 4 months ago
2008
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...
NECO
2010
13 years 3 months ago
2010
NECO
2008
13 years 4 months ago
2008
Deep Belief Networks (DBN) are generative neural network models with many layers of hidden explanatory factors, recently introduced by Hinton et al., along with a greedy layer-wis...