Current networked society present learners with challenges that cannot be sufficiently coped with in educational contexts that are characterized by transmission or participation ep...
In this paper, we present an experimental methodology and results for a machine learning approach to learning opening strategy in the game of Go, a game for which the best compute...
This paper studies the problem of learning from ambiguous supervision, focusing on the task of learning semantic correspondences. A learning problem is said to be ambiguously supe...
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
Abstract--In the Relational Reinforcement learning framework, we propose an algorithm that learns an action model allowing to predict the resulting state of each action in any give...