This paper presents a novel framework for simultaneously learning representation and control in continuous Markov decision processes. Our approach builds on the framework of proto...
This paper presents a novel semisupervised learning algorithm called Active Deep Networks (ADN), to address the semi-supervised sentiment classification problem with active learni...
We present an extension to a recent method for learning of nonlinear manifolds, which allows to incorporate general cost functions. We focus on the -insensitive loss and visually d...
Heuristic search effectiveness depends directly upon the quality of heuristic evaluations of states in the search space. We show why ordinal correlation is relevant to heuristic se...
Abstract. We introduce new approaches intended to speed up determining the satisfiability of a given Boolean formula expressed as a conjunction of Boolean functions. A common prac...