In this paper we give a fully dynamic approximation scheme for maintaining all-pairs shortest paths in planar networks. Given an error parameter ε such that 0 < ε, our algorit...
Abstract--This article deals with the issue of concept learning and tries to have a game theoretic view over the process of cooperative concept learning among agents in a multi-age...
This paper presents an active learning method that directly optimizes expected future error. This is in contrast to many other popular techniques that instead aim to reduce versio...
A graph-based prior is proposed for parametric semi-supervised classification. The prior utilizes both labelled and unlabelled data; it also integrates features from multiple view...
Balaji Krishnapuram, David Williams, Ya Xue, Alexa...
In many real-world domains, supervised learning requires a large number of training examples. In this paper, we describe an active learning method that uses a committee of learner...