Single Class Universum-SVM

This paper extends the idea of Universum learning [1, 2] to single - cla ss learning problems. We propose Single Class Universum - SVM setting that incorporates a priori knowledge (in the form of additional data samples) into the single class estimation problem . Th ese additional data samples or U niversum belong to the same applic ati on domain as (positive) data samples from a single class (of interest), but they follow a different distr ibution . Proposed methodology for single class U - SVM is based on the known connection between binary classification and single class learning formul ations [3]. S everal empirical comparisons are presented to illustrate the utility of the proposed approach.