In this paper, it is shown how to extract a hypothesis with small risk from the ensemble of hypotheses generated by an arbitrary on-line learning algorithm run on an independent an...
This paper presents a novel approach for online subspace learning based on an incremental version of the nonparametric discriminant analysis (NDA). For many real-world applications...
Guided by the goal of obtaining an optimization algorithm that is both fast and yields good generalization, we study the descent direction maximizing the decrease in generalizatio...
Nicolas Le Roux, Pierre-Antoine Manzagol, Yoshua B...
For a large class of applications, there is time to train the system. In this paper, we propose a learning-based approach to patch perspective rectification, and show that it is b...
Stefan Hinterstoisser, Selim Benhimane, Nassir Nav...
Abstract. Traditionally, medical education has used live patients to teach medical procedures. This carries a significant risk to patients. As learning technology advances, the ear...
Pablo Moreno-Ger, Carl Blesius, Paul Currier, Jos&...