中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Multi-class classification via discriminative multiple subspace learning

文献类型:会议论文

作者Tang, Tang; Qiao, Hong; Zheng, Suiwu
出版日期2013
会议名称International Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC)
会议日期DEC 20-22, 2013
会议地点Shenyang, PEOPLES R CHINA
关键词subspace learning generative model discriminative model
通讯作者Tang, T
英文摘要Subspace learning has long been a fundamental yet important problem of modeling data distributions. In this paper, we propose to learn multiple linear subspaces in a supervised way for multi-classclassification. To this end, a discriminative term redefining decision margin in terms of reconstruction error is incorporated into the model. The term enjoys similar properties of hinge loss function to the benefit of classification and leads to a training process seeking the balance between unsupervisedlearning and supervised learning. In the experiments on written digits dataset, our algorithm outperforms other methods proposed recently in both accuracy and computation efficiency.
会议录PROCEEDINGS 2013 INTERNATIONAL CONFERENCE ON MECHATRONIC SCIENCES, ELECTRIC ENGINEERING AND COMPUTER (MEC)
源URL[http://ir.ia.ac.cn/handle/173211/12868]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组
推荐引用方式
GB/T 7714
Tang, Tang,Qiao, Hong,Zheng, Suiwu. Multi-class classification via discriminative multiple subspace learning[C]. 见:International Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC). Shenyang, PEOPLES R CHINA. DEC 20-22, 2013.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。