Nonnegative matrix factorization and its applications in pattern recognition

查看全文 作　　者：LlU Weixiang ZHENG Nanning YOU [1]Qubo 机构地区：[1]Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an 710049, China 出　　处：《Chinese Science Bulletin》索引2006年第51卷第1期,共12页 基　　金：supported by the National Natural Science Foundation of China(Grant Nos.60205001 and 60021302). 摘　　要：Matrix factorization is an effective tool for large-scale data processing and analysis. Non- negative matrix factorization (NMF) method, which decomposes the nonnegative matrix into two non- negative factor matrices, provides a new way for ma- trix factorization. NMF is significant in intelligent information processing and pattern recognition. This paper firstly introduces the basic idea of NMF and some new relevant methods. Then we discuss the loss functions and relevant algorithms of NMF in the framework of probabilistic models based on our re- searches, and the relationship between NMF and information processing of perceptual process. Finally, we make use of NMF to deal with some practical questions of pattern recognition and point out some open problems for NMF. 关 键 词：特征抽取 NMF 模式识别 计算机