Laboratory for Information Theory, Department of Electrical Engineering, Delft University of Technology, Delft, The Netherlands;Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A.
Abstract:
An upperbound to the probability of error per class in a multivariate pattern classification is derived. The bound, given by is derived with minimal assumptions; specifically the mean vectors exist and are distinct and the covariance matrices exist and are non-singular. No other assumptions are made about the nature of the distributions of the classes. In equation (i) N is the number of features in the feature (vector) space and Ri is a measure of the “radial neighbourhood” of a class. An expression for Ri is developed. A comparison to the multivariate Gaussian hypothesis is presented.