CASIA OpenIR  > 模式识别国家重点实验室  > 模式分析与学习
Integrating supervised subspace criteria with restricted Boltzmann Machine for feature extraction
Xie, Guo-Sen; Zhang, Xu-Yao; Zhang, Yan-Ming; Liu, Cheng-Lin
2014
Conference NameInternational Joint Conference on Neural Networks (IJCNN)
Source PublicationProcceding of IJCNN 2014
Conference Date2014
Conference Place北京
AbstractRestricted Boltzmann Machine (RBM) is a widely
used building-block in deep neural networks. However, RBM is
an unsupervised model which can not exploit the rich supervised
information of data. Therefore, we consider combining the
descriptive (generative) ability of RBM with the discriminative
ability of supervised subspace models, i.e., Fisher linear discriminant analysis (FDA), marginal Fisher analysis (MFA), and heat
kernel MFA (hkMFA). Specifically, the hidden layer of RBM is
regularized by the supervised subspace criteria, and the joint
learning model can then be efficiently optimized by gradient
descent and graph construction (used to define the scatter matrix
in the subspace models) on mini-batch data. Compared with the
traditional subspace models (FDA, MFA, hkMFA), the proposed
hybrid models are essentially nonlinear and can be optimized
by gradient descent instead of eigenvalue decomposition. More
importantly, traditional subspace models can only reduce the
dimensionality (because of linear transformation), while the
proposed models can also increase the dimensionality for better
class discrimination. Experiments on three databases demonstrate
that the proposed hybrid models outperform both RBM and their
counterpart subspace models (FDA, MFA, hkMFA) consistently.

KeywordRbm
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/11958
Collection模式识别国家重点实验室_模式分析与学习
Corresponding AuthorXie, Guo-Sen
Recommended Citation
GB/T 7714
Xie, Guo-Sen,Zhang, Xu-Yao,Zhang, Yan-Ming,et al. Integrating supervised subspace criteria with restricted Boltzmann Machine for feature extraction[C],2014.
Files in This Item: Download All
File Name/Size DocType Version Access License
IJCNN14_paper.pdf(494KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xie, Guo-Sen]'s Articles
[Zhang, Xu-Yao]'s Articles
[Zhang, Yan-Ming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xie, Guo-Sen]'s Articles
[Zhang, Xu-Yao]'s Articles
[Zhang, Yan-Ming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xie, Guo-Sen]'s Articles
[Zhang, Xu-Yao]'s Articles
[Zhang, Yan-Ming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: IJCNN14_paper.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.