An entropic approach to dimensionality reduction on discrete processes

✍ Scribed by M.J del Moral; M.J Valderrama

• Publisher: Elsevier Science
• Year: 1999
• Tongue: English
• Weight: 176 KB
• Volume: 31
• Category: Article
• ISSN: 0167-9473
• DOI: 10.1016/s0167-9473(99)00013-4

✦ Synopsis

This paper generalizes the Watanabe method for class discrimination with the purpose of formulating dynamic random models starting from sample information. Such technique pursues, through the study of the eigenvalues, the reduction of the dimensionality in the representation space. We also describe an algorithm that allows the reconstruction and the approximation by dimensionality reduction for the original information. An illustration with a theoretical model reveals the great compression power this scheme produces, as well as the goodness of the approximations by dimensionality reduction. Two-class case is brie y discussed and an algorithm for reconstruction and classiÿcation is suggested. An application to climatological data shows results similar to the one-class case as far as dimensionality reduction goes. A reasonable classiÿcation rate is also obtained.