We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
Abstract. Weighted distance measure and discriminative training are two different approaches to enhance VQ-based solutions for speaker identification. To account for varying import...
Many computer vision tasks may be expressed as the problem of learning a mapping between image space and a parameter space. For example, in human body pose estimation, recent rese...
Ramanan Navaratnam, Andrew W. Fitzgibbon, Roberto ...
Two operations commute if executing them serially in either order results in the same change of state. In a system in which commands may be issued simultaneously by different use...
Greg Dennis, Robert Seater, Derek Rayside, Daniel ...
We propose a new fault localization technique for software bugs in large-scale computing systems. Our technique always collects per-process function call traces of a target system...