We combine three threads of research on approximate dynamic programming: sparse random sampling of states, value function and policy approximation using local models, and using lo...
We motivate and define a category of topological domains, whose objects are certain topological spaces, generalising the usual -continuous dcppos of domain theory. Our category su...
The incremental parsing (IP) algorithm has been successfully used in real-time applications, due to its efficiency in modeling musical style. For example, musical systems using IP...
Giordano Ribeiro de Eulalio Cabral, Jean-Pierre Br...
s, covering different levels of abstraction over the information exchanged. As the protocol is layered, we can discuss interaction in terms of different levels of granularity, bett...
David J. Duke, David A. Duce, Philip J. Barnard, J...
We present a new approach to bounding the true error rate of a continuous valued classifier based upon PAC-Bayes bounds. The method first constructs a distribution over classifier...