When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
In biology, many organisms coordinate their interactions in a self-organizing and emergent way solely by means of indirect communication based on chemical substances. These so-cal...
Robust Bayesian inference is the calculation of posterior probability bounds given perturbations in a probabilistic model. This paper focuses on perturbations that can be expresse...
In this paper, we study face hallucination, or synthesizing a high-resolution face image from an input low-resolution image, with the help of a large collection of other high-reso...
With the rapid performance improvements in low-cost PCs, it becomes increasingly practical and cost-effective to implement large-scale video-on-demand (VoD) systems around parallel...