Abstract. We consider the problem of predicting how a user will continue a given initial text fragment. Intuitively, our goal is to develop a “tab-complete” function for natura...
Generic ensemble methods can achieve excellent learning performance, but are not good candidates for active learning because of their different design purposes. We investigate how...
: In scientific digital libraries many documents such as publications, technical reports, theses, etc. could be used as basic data supports for distance learning in the universitie...
This paper describes a program of research designed to understand how knowledge-sharing and learning can be supported in virtual communities. To conduct this research, we propose ...
Michael Bieber, Il Im, Ronald E. Rice, Ricki Goldm...
In this paper we describe an unsupervised robot learning method which is based on the robot learning a mapping between sensors and trajectory velocities. This enables the robot to...