Integrating supervised subspace criteria with restricted Boltzmann Machine for feature extraction

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 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
会议名称	International Joint Conference on Neural Networks (IJCNN)
会议录名称	Procceding of IJCNN 2014
会议日期	2014
会议地点	北京
摘要	Restricted 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.
关键词	Rbm
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11958
专题	多模态人工智能系统全国重点实验室_模式分析与学习
通讯作者	Xie, Guo-Sen
推荐引用方式 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.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
IJCNN14_paper.pdf（494KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载