Sciweavers

9 search results - page 1 / 2
» Training restricted Boltzmann machines using approximations ...
Sort
View
ICML
2008
IEEE
14 years 4 months ago
Training restricted Boltzmann machines using approximations to the likelihood gradient
A new algorithm for training Restricted Boltzmann Machines is introduced. The algorithm, named Persistent Contrastive Divergence, is different from the standard Contrastive Diverg...
Tijmen Tieleman
ICANN
2010
Springer
13 years 4 months ago
Empirical Analysis of the Divergence of Gibbs Sampling Based Learning Algorithms for Restricted Boltzmann Machines
Abstract. Learning algorithms relying on Gibbs sampling based stochastic approximations of the log-likelihood gradient have become a common way to train Restricted Boltzmann Machin...
Asja Fischer, Christian Igel
JMLR
2010
139views more  JMLR 2010»
12 years 10 months ago
Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann Machines
Alternating Gibbs sampling is the most common scheme used for sampling from Restricted Boltzmann Machines (RBM), a crucial component in deep architectures such as Deep Belief Netw...
Guillaume Desjardins, Aaron C. Courville, Yoshua B...
NECO
2008
170views more  NECO 2008»
13 years 3 months ago
Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
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...
Nicolas Le Roux, Yoshua Bengio
NECO
2010
136views more  NECO 2010»
13 years 2 months ago
Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines
To allow the hidden units of a restricted Boltzmann machine to model the transformation between two successive images, Memisevic and Hinton (2007) introduced three-way multiplicat...
Roland Memisevic, Geoffrey E. Hinton