We present a new technique that employs support vector machines and Gaussian mixture densities to create a generative/discriminative joint classifier. In the past, several approac...
A mapping of unit vectors onto a 5D hypersphere is used to model and partition ODFs from HARDI data. This mapping has a number of useful and interesting properties and we make a li...
This paper extends our previous work on feature transformationbased support vector machines for speaker recognition by proposing a joint MAP adaptation of feature transformation (...
We construct a mixture of locally linear generative models of a collection of pixel-based images of digits, and use them for recognition. Different models of a given digit are use...
This correspondence presents new approaches for optimizing kurtosis-based separation criteria in the case of long mixture recordings. Our methods are based on a multivariate polyno...