Many real-world classification tasks involve the prediction of multiple, inter-dependent class labels. A prototypical case of this sort deals with prediction of a sequence of labe...
The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
We have developed a system that allows users to add annotations immediately onto a Web page they are viewing, and share the information via a network. A novel feature of our metho...
We present a new data structure that facilitates approximate nearest neighbor searches on a dynamic set of points in a metric space that has a bounded doubling dimension. Our data...
Ad hoc networks formed without the aid of any established infrastructure are typically multi-hop networks. Location dependent contention and "hidden terminal" problem ma...