Boltzmann machines with clusters of stochastic binary units

Da Teng; Zhang Li; Guanghong Gong; Liang Han

doi:10.1142/S1793962316500185

Boltzmann machines with clusters of stochastic binary units

Da Teng^*
, Zhang Li
, Guanghong Gong
, Liang Han

^*Corresponding author for this work

Beihang University
Yunnan University

Research output: Contribution to journal › Article › peer-review

Abstract

The original restricted Boltzmann machines (RBMs) are extended by replacing the binary visible and hidden variables with clusters of binary units, and a new learning algorithm for training deep Boltzmann machine of this new variant is proposed. The sum of binary units of each cluster is approximated by a Gaussian distribution. Experiments demonstrate that the proposed Boltzmann machines can achieve good performance in the MNIST handwritten digital recognition task.

Original language	English
Article number	1650018
Journal	International Journal of Modeling, Simulation, and Scientific Computing
Volume	7
Issue number	2
DOIs	https://doi.org/10.1142/S1793962316500185
State	Published - 1 Jun 2016

Keywords

Restricted Boltzmann machines
machine learning
unsupervised learning

Access to Document

10.1142/S1793962316500185

Cite this

@article{0c7b43d2961a437bb648eaa7f1946626,

title = "Boltzmann machines with clusters of stochastic binary units",

abstract = "The original restricted Boltzmann machines (RBMs) are extended by replacing the binary visible and hidden variables with clusters of binary units, and a new learning algorithm for training deep Boltzmann machine of this new variant is proposed. The sum of binary units of each cluster is approximated by a Gaussian distribution. Experiments demonstrate that the proposed Boltzmann machines can achieve good performance in the MNIST handwritten digital recognition task.",

keywords = "Restricted Boltzmann machines, machine learning, unsupervised learning",

author = "Da Teng and Zhang Li and Guanghong Gong and Liang Han",

note = "Publisher Copyright: {\textcopyright} 2016 World Scientific Publishing Company.",

year = "2016",

month = jun,

day = "1",

doi = "10.1142/S1793962316500185",

language = "英语",

volume = "7",

journal = "International Journal of Modeling, Simulation, and Scientific Computing",

issn = "1793-9623",

publisher = "World Scientific",

number = "2",

}

TY - JOUR

T1 - Boltzmann machines with clusters of stochastic binary units

AU - Teng, Da

AU - Li, Zhang

AU - Gong, Guanghong

AU - Han, Liang

PY - 2016/6/1

Y1 - 2016/6/1

N2 - The original restricted Boltzmann machines (RBMs) are extended by replacing the binary visible and hidden variables with clusters of binary units, and a new learning algorithm for training deep Boltzmann machine of this new variant is proposed. The sum of binary units of each cluster is approximated by a Gaussian distribution. Experiments demonstrate that the proposed Boltzmann machines can achieve good performance in the MNIST handwritten digital recognition task.

AB - The original restricted Boltzmann machines (RBMs) are extended by replacing the binary visible and hidden variables with clusters of binary units, and a new learning algorithm for training deep Boltzmann machine of this new variant is proposed. The sum of binary units of each cluster is approximated by a Gaussian distribution. Experiments demonstrate that the proposed Boltzmann machines can achieve good performance in the MNIST handwritten digital recognition task.

KW - Restricted Boltzmann machines

KW - machine learning

KW - unsupervised learning

UR - https://www.scopus.com/pages/publications/84973352075

U2 - 10.1142/S1793962316500185

DO - 10.1142/S1793962316500185

M3 - 文章

AN - SCOPUS:84973352075

SN - 1793-9623

VL - 7

JO - International Journal of Modeling, Simulation, and Scientific Computing

JF - International Journal of Modeling, Simulation, and Scientific Computing

IS - 2

M1 - 1650018

ER -

Boltzmann machines with clusters of stochastic binary units

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this