To perform automatic, unconscious inference, the human brain must solve the "binding problem" by correctly grouping properties with objects. Temporal binding models like...
We propose a Bayesian framework for representing and recognizing local image motion in terms of two basic models: translational motion and motion boundaries. Motion boundaries are ...
We present a principled Bayesian framework for modeling partial memberships of data points to clusters. Unlike a standard mixture model which assumes that each data point belongs ...
Katherine A. Heller, Sinead Williamson, Zoubin Gha...
Most real-world data is stored in relational form. In contrast, most statistical learning methods work with "flat" data representations, forcing us to convert our data i...
Lise Getoor, Nir Friedman, Daphne Koller, Benjamin...
Current CMOS technologies are characterized by interconnect lines with increased relative resistance w.r.t. driver output resistance. Designs generate signal waveshapes that are v...