An evolutionary approach to design communication protocols from scenario-based specifications is presented. It enables to automatically generate finite-state models of protocol ent...
Machine learning techniques are applicable to computer system optimization. We show that shared memory multiprocessors can successfully utilize machine learning algorithms for mem...
M. F. Sakr, Steven P. Levitan, Donald M. Chiarulli...
We introduce the controlled predictive linearGaussian model (cPLG), a model that uses predictive state to model discrete-time dynamical systems with real-valued observations and v...
The Gesture and Activity Recognition Toolit (GART) is a user interface toolkit designed to enable the development of gestureplications. GART provides an abstraction to machine lear...
Kent Lyons, Helene Brashear, Tracy L. Westeyn, Jun...
We have designed, implemented, and proved the correctness of a compiler generator that accepts action semantic descriptions of imperative programming languages. The generated comp...