We introduce a novel computational method for a Mumford-Shah functional, which decomposes a given image into smooth regions separated by closed curves. Casting this as a shape opti...
—In kernel based regression techniques (such as Support Vector Machines or Least Squares Support Vector Machines) it is hard to analyze the influence of perturbed inputs on the ...
Abstract. We present a new “lifting” approach for the solution of nonlinear optimization problems (NLPs) that have objective and constraint functions with intermediate variable...
Abstract—The future Internet is expected to support applications with quality of service (QoS) requirements. For this end several mechanisms are suggested in the IETF to support ...
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...