Gaussian kernels with flexible variances provide a rich family of Mercer kernels for learning algorithms. We show that the union of the unit balls of reproducing kernel Hilbert s...
In modelling nonstationary sources, one possible strategy is to define a latent process of strictly positive variables to model variations in second order statistics of the underly...
Abstract--We investigate parameter-based and distributionbased approaches to regularizing the generative, similarity-based classifier called local similarity discriminant analysis ...