We propose a novel kernel regression algorithm which takes into account order preferences on unlabeled data. Such preferences have the form that point x1 has a larger target value...
The generalization of policies in reinforcement learning is a main issue, both from the theoretical model point of view and for their applicability. However, generalizing from a se...
This paper presents a general framework for adapting any generative (model-based) clustering algorithm to provide balanced solutions, i.e., clusters of comparable sizes. Partition...
We present a new paradigm, called “Global ISP” (G-ISP). Its goal is to solve, or at least alleviate, problems of inter-domain routing, such as slow convergence, and lack of Qo...
We present a class of nonlinear adaptive image restoration filters which may be steered to preserve sharp edges and contrasts in the restorations. From a theoretical point of view ...