Sciweavers

Share
4 search results - page 1 / 1
» Using fast weights to improve persistent contrastive diverge...
Sort
View
ICML
2009
IEEE
10 years 21 days ago
Using fast weights to improve persistent contrastive divergence
The most commonly used learning algorithm for restricted Boltzmann machines is contrastive divergence which starts a Markov chain at a data point and runs the chain for only a few...
Tijmen Tieleman, Geoffrey E. Hinton
ICML
2008
IEEE
10 years 6 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
CVPR
2009
IEEE
1081views Computer Vision» more  CVPR 2009»
11 years 1 months ago
Learning Real-Time MRF Inference for Image Denoising
Many computer vision problems can be formulated in a Bayesian framework with Markov Random Field (MRF) or Conditional Random Field (CRF) priors. Usually, the model assumes that ...
Adrian Barbu (Florida State University)
ALGORITHMICA
2005
225views more  ALGORITHMICA 2005»
9 years 5 months ago
Better Alternatives to OSPF Routing
The current standard for intra-domain network routing, Open Shortest Path First (OSPF), suffers from a number of problems--the tunable parameters (the weights) are hard to optimiz...
Jessica H. Fong, Anna C. Gilbert, Sampath Kannan, ...
books