The design productivity gap has been recognized by the semiconductor industry as one of the major threats to the continued growth of system-on-chips and embedded systems. Ad-hoc s...
Jean-Pierre Talpin, David Berner, Sandeep K. Shukl...
We propose a novel a framework for deriving approximations for intractable probabilistic models. This framework is based on a free energy (negative log marginal likelihood) and ca...
—Many traditional two-view stereo algorithms explicitly or implicitly use the frontal parallel plane assumption when exploiting contextual information since, e.g., the smoothness...
We investigate a hybrid method which improves the quality of state inference and parameter estimation in blind deconvolution of a sparse source modeled by a Bernoulli-Gaussian pro...
We present a new approximate inference algorithm for Deep Boltzmann Machines (DBM's), a generative model with many layers of hidden variables. The algorithm learns a separate...