Generalized Kernel Restricted Boltzmann Machine 


Vol. 45,  No. 5, pp. 783-789, May  2020
10.7840/kics.2020.45.5.783


PDF
  Abstract

This paper presents a generalized form of kernel restricted Boltzmann machine (KRBM). The variance terms in the generalized KRBM are included to model the uncertainty of the visible and hidden units of KRBM with Gaussian distribution. The gradient-based contrastive divergence algorithm is used for the training of the generalized KRBM, and the parameter update rules are derived for the learning. Experimental results on MNIST and STL-10 dataset show that the proposed approach outperforms the conventional KRBM in terms of reconstruction error and classification accuracy.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

D. K. Kim, "Generalized Kernel Restricted Boltzmann Machine," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 5, pp. 783-789, 2020. DOI: 10.7840/kics.2020.45.5.783.

[ACM Style]

Dong Kook Kim. 2020. Generalized Kernel Restricted Boltzmann Machine. The Journal of Korean Institute of Communications and Information Sciences, 45, 5, (2020), 783-789. DOI: 10.7840/kics.2020.45.5.783.

[KICS Style]

Dong Kook Kim, "Generalized Kernel Restricted Boltzmann Machine," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 5, pp. 783-789, 5. 2020. (https://doi.org/10.7840/kics.2020.45.5.783)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880