Multiple Attribute Learning with Canonical Correlation Analysis and Em Algorithm

This paper presents a new framework of learning pattern recognition, called \multiple attribute learning". In usual setting of pattern recognition, target patterns have several attribute such as color, size, shape, and we can classify the patterns in several ways by their color, by their size, or by their shape. in normal pattern recognition problem, an attribute or a mode of classi cation is chosen in advance and the problem is simpli ed. To the contrary, the problem considered in this paper is to make the learning system solve multiple classi cation problems at once. That is, a mixture of learning data set for multiple classi cation problems are given to the learning system at once and the system learn multiple classi cation rules from the data. We propose a method to solve this problem using canonical correlation analysis and EM algorithm. The effectiveness of the method is demonstrated by experiments. Information Science Division y Machine Intelligence Division