We present a large-margin formulation and algorithm for structured output prediction that allows the use of latent variables. Our proposal covers a large range of application prob...
Research in reinforcementlearning (RL)has thus far concentrated on two optimality criteria: the discounted framework, which has been very well-studied, and the averagereward frame...
This paper presents the design and testing of Kana Warrior, a new interface for basic Japanese character recognition based on a game-style user interface. Kana Warrior is a game d...
Gradiance On-Line Accelerated Learning GOAL is a system for creating and automatically grading homeworks, programming laboratories, and tests. Through the concept of root questi...
Finding a constraint network that will be efficiently solved by a constraint solver requires a strong expertise in Constraint Programming. Hence, there is an increasing interest i...