Abstract. We address the problem of visual event recognition in surveillance where noise and missing observations are serious problems. Common sense domain knowledge is exploited t...
Universal induction solves in principle the problem of choosing a prior to achieve optimal inductive inference. The AIXI theory, which combines control theory and universal induct...
For many types of machine learning algorithms, one can compute the statistically optimal" way to select training data. In this paper, we review how optimal data selection tec...
David A. Cohn, Zoubin Ghahramani, Michael I. Jorda...
In this paper, we develop a theory of modular design and refinement of hierarchical hybrid systems. In particular, we present compositional trace-based semantics for the language ...
We describe a unified representation of occluders in light transport and photography using shield fields: the 4D attenuation function which acts on any light field incident on an ...
Douglas Lanman, Ramesh Raskar, Amit K. Agrawal, Ga...