We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding tasks (multi-class classification). Existing multi-class a...
Intelligent planning algorithms such as the Partially Observable Markov Decision Process (POMDP) have succeeded in dialog management applications [10, 11, 12] because of their rob...
This position paper discusses different philosophical views of learning and the consequences of these different epistemologies on the design of online learning environments. Acade...
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...
In the last decade, connectionist models have been proposed that can process structured information directly. These methods, which are based on the use of graphs for the representa...
Werner Uwents, Gabriele Monfardini, Hendrik Blocke...