Next Article in Journal
Acknowledgement to Reviewers of Entropy in 2015
Previous Article in Journal
The Entropy of Laughter: Discriminative Power of Laughter’s Entropy in the Diagnosis of Depression
Article Menu

Export Article

Open AccessArticle
Entropy 2016, 18(1), 35; doi:10.3390/e18010035

Average Contrastive Divergence for Training Restricted Boltzmann Machines

1
Center for Intelligence Science and Technology, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China
2
School of Mathematic and Information Science, Henan Polytechnic University, Jiaozuo 454000, China
*
Author to whom correspondence should be addressed.
Academic Editor: Kevin Knuth
Received: 22 September 2015 / Revised: 11 January 2016 / Accepted: 15 January 2016 / Published: 21 January 2016
View Full-Text   |   Download PDF [271 KB, uploaded 21 January 2016]   |  

Abstract

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 algorithm called average contrastive divergence (ACD) for training RBMs. It is an improved CD algorithm, and it is different from the traditional CD algorithm. Finally, we obtain some experimental results. The results show that the new algorithm is a better approximation of the log-likelihood gradient method and outperforms the traditional CD algorithm. View Full-Text
Keywords: restricted Boltzmann machines; contrastive divergence; log-likelihood; gradient method; average contrastive divergence restricted Boltzmann machines; contrastive divergence; log-likelihood; gradient method; average contrastive divergence
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

Scifeed alert for new publications

Never miss any articles matching your research from any publisher
  • Get alerts for new papers matching your research
  • Find out the new papers from selected authors
  • Updated daily for 49'000+ journals and 6000+ publishers
  • Define your Scifeed now

SciFeed Share & Cite This Article

MDPI and ACS Style

Ma, X.; Wang, X. Average Contrastive Divergence for Training Restricted Boltzmann Machines. Entropy 2016, 18, 35.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Entropy EISSN 1099-4300 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top