This paper presents a new method for integrating di erent low level vision modules, stereo and shape from shading, in order to improve the 3D reconstruction of visible surfaces of objects from intensity images. The integration process is based on correcting the 3D visible surface obtained from shape from shading using the sparse depth measurements from the stereo module by tting a surface into ...

| Since manufacturing processes inherently uctuate, LSI chips which are produced from the same design have di erent propagation delays. However, the di erence in delays caused by the the process uctuation has rarely been considered in most high-level synthesis systems which were developed before. This paper presents a new approach to module selection in high-level synthesis, which exploits di e...

Properties of probabilistic as well as \probabilistic plus nondeterministic" pushdown automata and auxiliary pushdown automata are studied. These models are analogous to their counterparts with nondeterministic and alternating states. Complete characterizations in terms of well-known complexity classes are given for the classes of languages recognized by polynomial time-bounded, logarithmic spa...

Starting from the most general formulation of stochastic thermodynamics—i.e. a thermodynamically consistent nonautonomous stochastic dynamics describing systems in contact with several reservoirs—, we de€ne a procedure to identify the conservative and the minimal set of nonconservative contributions in the entropy production. Œe former is expressed as the di‚erence between changes caused by tim...

This paper presents an assignment model of CEOs and …rms. The distributions of CEO pay levels and …rms’market values are analyzed as the competitive equilibrium of a matching market where talents, as well as CEO positions, are scarce. It is shown how the observed joint distribution of CEO pay and market value can then be used to infer the economic value of underlying ability di¤erences. The var...

We introduce the rst algorithm for o -policy temporal-di erence learning that is stable with linear function approximation. O policy learning is of interest because it forms the basis for popular reinforcement learning methods such as Q-learning, which has been known to diverge with linear function approximation, and because it is critical to the practical utility of multi-scale, multi-goal, le...

We present a new connectionist framework for solving deterministic sequential decision problems based on temporal diierence learning and dynamic programming. The framework will be compared to Tesauro's approach of learning a strategy for playing backgammon, a proba-bilistic board game. It will be shown that his approach is not applicable for deterministic games, but simple modiications lead to ...

For the rst interactive Cross Language Evaluation Forum the Maryland team focused on com parison of term for term gloss translation with full machine translation for the document selection task The results show that searchers are able to make relevance judgments with translations from either approach and the machine translation system achieved better e ectiveness than the gloss translation stra...

For the rst interactive Cross-Language Evaluation Forum, the Maryland team focused on comparison of term-for-term gloss translation with full machine translation for the document selection task. The results show that (1) searchers are able to make relevance judgments with translations from either approach, and (2) the machine translation system achieved better e ectiveness than the gloss transl...

The success of reinforcement learning in practical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experiments in this area have produced mixed results; there have been both notable successes and notable disappointments. Theory has been scarce, mostly due to the difculty of reasoning about function approximators that gen...