Many learning algorithms rely on the curvature (in particular, strong convexity) of regularized objective functions to provide good theoretical performance guarantees. In practice...
JIGSAW is a well-known technique for collaborative learning. Students typically use it in a face-to-face setting without computer support. This paper describes a Webbased tool for...
Most modern computer vision systems for high-level
tasks, such as image classification, object recognition and
segmentation, are based on learning algorithms that are
able to se...
Many problems in vision involve the prediction of a class label for each frame in an unsegmented sequence. In this paper, we develop a discriminative framework for simultaneous se...
Learning Bayesian Belief Networks (BBN) from corpora and incorporating the extracted inferring knowledge with a Support Vector Machines (SVM) classifier has been applied to charac...