Weight Uncertainty in Boltzmann Machine

doi:10.1007/s12559-016-9429-1

	Weight Uncertainty in Boltzmann Machine
	Zhang, Jian 1,2; Ding, Shifei 1,2; Zhang, Nan 1,2; Xue, Yu 3
	2016-12-01
发表期刊	Cognitive Computation
ISSN	1866-9956
卷号	8 期号:6 页码:1064-1073
摘要	Based on restricted Boltzmann machine (RBM), the deep learning models can be roughly divided into deep belief networks (DBNs) and deep Boltzmann machine (DBM). However, the overfitting problems commonly exist in neural networks and RBM models. In order to alleviate the overfitting problem, lots of research has been done. This paper alleviated the overfitting problem in RBM and proposed the weight uncertainty semi-restricted Boltzmann machine (WSRBM) to improve the ability of image recognition and image reconstruction. First, this paper built weight uncertainty RBM model based on maximum likelihood estimation. And in the experimental section, this paper verified the effectiveness of the weight uncertainty deep belief network and the weight uncertainty deep Boltzmann machine. Second, in order to obtain better reconstructed images, this paper used the semi-restricted Boltzmann machine (SRBM) as the feature extractor and built the WSRBM. Lastly, this paper used hybrid Monte Carlo sampling and cRBM to improve the classification ability of WSDBM. The experiments showed that the weight uncertainty RBM, weight uncertainty DBN and weight uncertainty DBM were effective compared with the dropout method. And the WSDBM model performed well in image recognition and image reconstruction as well. This paper introduced the weight uncertainty method to RBM, and proposed a WSDBM model, which was effective in image recognition and image reconstruction.
关键词	RBM DBM DBN Weight uncertainty
DOI	10.1007/s12559-016-9429-1
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61379101] ; National Natural Science Foundation of China[61672522] ; National Key Basic Research Program of China[2013CB329502] ; Priority Academic Program Development of Jiangsu Higer Education Institutions ; Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology
WOS研究方向	Computer Science ; Neurosciences & Neurology
WOS类目	Computer Science, Artificial Intelligence ; Neurosciences
WOS记录号	WOS:000389304300005
出版者	SPRINGER
引用统计	被引频次：10[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/7797
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Ding, Shifei
作者单位	1.China Univ Min & Technol, Sch Comp Sci & Technol, Xuzhou 221116, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Nanjing Univ Informat Sci & Technol, Coll Comp & Software, Nanjing 210044, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Jian,Ding, Shifei,Zhang, Nan,et al. Weight Uncertainty in Boltzmann Machine[J]. Cognitive Computation,2016,8(6):1064-1073.
APA	Zhang, Jian,Ding, Shifei,Zhang, Nan,&Xue, Yu.(2016).Weight Uncertainty in Boltzmann Machine.Cognitive Computation,8(6),1064-1073.
MLA	Zhang, Jian,et al."Weight Uncertainty in Boltzmann Machine".Cognitive Computation 8.6(2016):1064-1073.