Paper

Parallel Tempering for Training of Restricted Boltzmann Machines

Alternating Gibbs sampling between visible and latent units is the most common scheme used for sampling from Restricted Boltzmann Machines (RBM), a crucial component in deep architectures such as Deep Belief Networks (DBN). However, we find that it often does a very poor job of rendering the diversity of modes captured by the trained model. We suspect that this property hinders RBM training methods such as the Contrastive Divergence and Persistent Contrastive Divergence algorithm that rely on Gibbs sampling to approximate the likelihood gradient. To alleviate this problem, we explore the use of tempered Markov Chain Monte-Carlo for sampling in RBMs. We find both through visualization of samples and measures of likelihood on a toy dataset that it helps both sampling and learning.

http://jmlr.csail.mit.edu/proceedings/papers/v9/desjardins10a/desjardins10a.pdfPublished 2010-01-01Paper link

Authors: Guillaume Desjardins · Aaron Courville · Yoshua Bengio · Pascal Vincent · Olivier Delalleau

Topics

Relevant entities

People

Related coverage

Linked coverage will appear here.

Related events

Linked events will appear here.

Related discussions

Related discussion nodes will appear here.