Abstract— In their interactions with the world robots inevitably face equivalent action choices, situations in which multiple actions are equivalently applicable. In this paper, ...
In many prediction tasks, selecting relevant features is essential for achieving good generalization performance. Most feature selection algorithms consider all features to be a p...
Su-In Lee, Vassil Chatalbashev, David Vickrey, Dap...
We seek the scene interpretation that best explains image data. For example, we may want to infer the projected velocities (scene) which best explain two consecutive image frames ...
The authors present TWIG, a visually grounded wordlearning system that uses its existing knowledge of vocabulary, grammar, and action schemas to help it learn the meanings of new ...
This paper proposes an optimisation to the UK-means algorithm, which generalises the k-means algorithm to handle objects whose locations are uncertain. The location of each object...