When a large amount of data are missing, or when multiple hidden nodes exist, learning parameters in Bayesian networks (BNs) becomes extremely difficult. This paper presents a lea...
Abstract. We propose a method for automatically correcting the spherical topology of any segmentation under any digital connectivity. A multiple region growing process, concurrentl...
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
Image matching is a fundamental task for many applications of computer vision. Today it is very popular to represent two matched images as two bags of local descriptors, and the c...