The problem of character recognition in a book should be formulated significantly different from that of a single page or word. An ideal approach to design such a recognizer is to...
We consider the problem of optimality, in a minimax sense, and adaptivity to the margin and to regularity in binary classification. We prove an oracle inequality, under the margin ...
In this paper we study how to improve nearest neighbor classification by learning a Mahalanobis distance metric. We build on a recently proposed framework for distance metric lear...
An adaptive semi-supervised ensemble method, ASSEMBLE, is proposed that constructs classification ensembles based on both labeled and unlabeled data. ASSEMBLE alternates between a...
Striking a balance between rigidity and flexibility is a central challenge in designing business processes. Striking this balance begins on the type level, because expressiveness ...