Topologically Ordered Feature Extraction Based on Sparse Group Restricted Boltzmann Machines
Joint Authors
Fang, Zhixiang
Xiong, Shengwu
Zhang, Ruiling
Rong, Yi
Chen, Zhong
Kong, Xiangzhen
Source
Mathematical Problems in Engineering
Issue
Vol. 2015, Issue 2015 (31 Dec. 2015), pp.1-12, 12 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2015-09-27
Country of Publication
Egypt
No. of Pages
12
Main Subjects
Abstract EN
How to extract topologically ordered features efficiently from high-dimensional data is an important problem of unsupervised feature learning domains for deep learning.
To address this problem, we propose a new type of regularization for Restricted Boltzmann Machines (RBMs).
Adding two extra terms in the log-likelihood function to penalize the group weights and topologically ordered factors, this type of regularization extracts topologically ordered features based on sparse group Restricted Boltzmann Machines (SGRBMs).
Therefore, it encourages an RBM to learn a much smoother probability distribution because its formulations turn out to be a combination of the group weight-decay and topologically ordered factor regularizations.
We apply this proposed regularization scheme to image datasets of natural images and Flying Apsara images in the Dunhuang Grotto Murals at four different historical periods.
The experimental results demonstrate that the combination of these two extra terms in the log-likelihood function helps to extract more discriminative features with much sparser and more aggregative hidden activation probabilities.
American Psychological Association (APA)
Chen, Zhong& Xiong, Shengwu& Fang, Zhixiang& Zhang, Ruiling& Kong, Xiangzhen& Rong, Yi. 2015. Topologically Ordered Feature Extraction Based on Sparse Group Restricted Boltzmann Machines. Mathematical Problems in Engineering،Vol. 2015, no. 2015, pp.1-12.
https://search.emarefa.net/detail/BIM-1073354
Modern Language Association (MLA)
Chen, Zhong…[et al.]. Topologically Ordered Feature Extraction Based on Sparse Group Restricted Boltzmann Machines. Mathematical Problems in Engineering No. 2015 (2015), pp.1-12.
https://search.emarefa.net/detail/BIM-1073354
American Medical Association (AMA)
Chen, Zhong& Xiong, Shengwu& Fang, Zhixiang& Zhang, Ruiling& Kong, Xiangzhen& Rong, Yi. Topologically Ordered Feature Extraction Based on Sparse Group Restricted Boltzmann Machines. Mathematical Problems in Engineering. 2015. Vol. 2015, no. 2015, pp.1-12.
https://search.emarefa.net/detail/BIM-1073354
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1073354