Biologically focused, agent-based models need many parameters in order to simulate system dynamics. It is often essential to explore the consequences of many parameter vectors bef...
Several algorithms for global motion estimation in video sequences using pixel- or block-based approaches have been published. Most known pixel-based methods lack in performance w...
Michael Tok, Alexander Glantz, Marina Georgia Arva...
The scarcity of available multi-track recordings constitutes a severe constraint on the training of probabilistic models for voice extraction from polyphonic music. We propose a n...
One of the key issues in hardware/software{cosynthesis is precise estimation. The usual local estimation techniques are inadequate for globally optimising compilers and synthesis ...
Boltzmann machine is a classic model of neural computation, and a number of methods have been proposed for its estimation. Most methods are plagued by either very slow convergence...