Training restricted Boltzmann machines using approximations to the likelihood gradient
Training restricted Boltzmann machines using approximations to the likelihood gradient
T. Tieleman
2008 · DOI: 10.1145/1390156.1390290
International Conference on Machine Learning · 1,043 Citations
TLDR
A new algorithm for training Restricted Boltzmann Machines is introduced, which is compared to some standard Contrastive Divergence and Pseudo-Likelihood algorithms on the tasks of modeling and classifying various types of data.