Material Detail

Training Restricted Boltzmann Machines using Approximations to the Likelihood Gradient

Training Restricted Boltzmann Machines using Approximations to the Likelihood Gradient

This video was recorded at 25th International Conference on Machine Learning (ICML), Helsinki 2008. A new algorithm for training Restricted Boltzmann Machines is introduced. The algorithm, named Persistent Contrastive Divergence, is different from the standard Contrastive Divergence algorithms in that it aims to draw samples from almost exactly the model distribution. It is compared to some standard Contrastive Divergence algorithms on the tasks of modeling handwritten digits and classifying digit images by learning a model of the joint distribution of images and labels. The Persistent Contrastive Divergence algorithm outperforms other Contrastive Divergence algorithms, and is equally fast and simple.

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.