Classifiers are traditionally learned using sets of positive and negative training examples. However, often a classifier is required, but for training only an incomplete set of pos...
This article proposes an algorithm to automatically learn useful transformations of data to improve accuracy in supervised classification tasks. These transformations take the for...
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 many application domains there is a large amount of unlabeled data but only a very limited amount of labeled training data. One general approach that has been explored for util...
Avrim Blum, John D. Lafferty, Mugizi Robert Rweban...
In Kernel Fisher discriminant analysis (KFDA), we carry out Fisher linear discriminant analysis in a high dimensional feature space defined implicitly by a kernel. The performance...
Seung-Jean Kim, Alessandro Magnani, Stephen P. Boy...