Average Contrastive Divergence for Training Restricted Boltzmann Machines

Average Contrastive Divergence for Training Restricted Boltzmann Machines

This paper studies contrastive divergence (CD) learning algorithm and proposes a new algorithm for training restricted Boltzmann machines (RBMs). We derive that CD is a biased estimator of the log-likelihood gradient method and make an analysis of the bias. Meanwhile, we propose a new learning algor...

Full description

Bibliographic Details
Main Authors: Xuesi Ma, Xiaojie Wang
Format: Article
Language:English
Published: MDPI AG 2016-01-01
Series:Entropy
Subjects:
restricted Boltzmann machines
contrastive divergence
log-likelihood
gradient method
average contrastive divergence
Online Access:http://www.mdpi.com/1099-4300/18/1/35

Internet

http://www.mdpi.com/1099-4300/18/1/35

Similar Items