We introduce a semi-supervised learning estimator which tends to the first kernel principal component as the number of labeled points vanishes. We show application of the proposed...
Leonardo Angelini, Daniele Marinazzo, Mario Pellic...
We take a dual view of Markov processes ? advocated by Kozen ? as transformers of bounded measurable functions. We redevelop the theory of labelled Markov processes from this view ...
Philippe Chaput, Vincent Danos, Prakash Panangaden...
In the last years dependency parsing has been accomplished by machine learning–based systems showing great accuracy but usually under 90% for Labelled Attachment Score (LAS). Mal...
We start by showing that in an active learning setting, the Perceptron algorithm needs Ω( 1 ε2 ) labels to learn linear separators within generalization error ε. We then prese...
Sanjoy Dasgupta, Adam Tauman Kalai, Claire Montele...
Abstract. Interactively learning from a small sample of unlabeled examples is an enormously challenging task. Relevance feedback and more recently active learning are two standard ...
Charlie K. Dagli, ShyamSundar Rajaram, Thomas S. H...