Policy gradient approaches are a powerful instrument for learning how to interact with the environment. Existing approaches have focused on propositional and continuous domains on...
We describe the first tractable Gibbs sampling procedure for estimating phrase pair frequencies under a probabilistic model of phrase alignment. We propose and evaluate two nonpar...
Pictorial Structures (PS) define a probabilistic model of 2D articulated objects in images. Typical PS models assume an object can be represented by a set of rigid parts connecte...
Deep belief networks are a powerful way to model complex probability distributions. However, it is difficult to learn the structure of a belief network, particularly one with hidd...
Ryan Prescott Adams, Hanna M. Wallach, Zoubin Ghah...
Abstract. Clustering has recently enjoyed progress via spectral methods which group data using only pairwise affinities and avoid parametric assumptions. While spectral clustering ...