Optimally designing the location of training input points (active learning) and choosing the best model (model selection) are two important components of supervised learning and h...
We address the problem of evaluating the risk of a given model accurately at minimal labeling costs. This problem occurs in situations in which risk estimates cannot be obtained f...
Christoph Sawade, Niels Landwehr, Steffen Bickel, ...
Abstract. When faced with the task of building accurate classifiers, active learning is often a beneficial tool for minimizing the requisite costs of human annotation. Traditional ...
Non-parametric data representation can be done by means of a potential function. This paper introduces a methodology for finding modes of the potential function. Two different me...
Abstract. The original Semantic Web vision was explicit in the need for intelligent autonomous agents that would represent users and help them navigate the Semantic Web. We argue t...
Gunnar Aastrand Grimnes, Peter Edwards, Alun D. Pr...