This paper describes the development of a Question Answering (QA) system and its evaluation results in the Romanian-English cross-lingual track organized as part of the CLEF1 2006 ...
Georgiana Puscasu, Adrian Iftene, Ionut Pistol, Di...
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...
The state of the science of information security is astonishingly rich with solutions and tools to incrementally and selectively solve the hard problems. In contrast, the state of...
FLAVERS, a tool for verifying properties of concurrent systems, uses composite data flow analysis to incrementally improve the precision of the results of its verifications. Altho...
We present a new heuristic approach for maximal constraint satisfaction of overconstrained problems (MAX-CSP). This approach is based on a formulation of CSP as an optimization pro...