Data locality is critical to achievinghigh performance on large-scale parallel machines. Non-local data accesses result in communication that can greatly impact performance. Thus ...
Bayesian belief propagation in graphical models has been recently shown to have very close ties to inference methods based in statistical physics. After Yedidia et al. demonstrate...
We address the problem of Bayesian image reconstruction with a prior that captures the notion of a clustered intensity histogram. The problem is formulated in the framework of a j...
We present a novel framework for multiple object tracking in which the problems of object detection and data association are expressed by a single objective function. The framewor...
Zheng Wu, Ashwin Thangali, Stan Sclaroff, Margrit ...
One might imagine that AI systems with harmless goals will be harmless. This paper instead shows that intelligent systems will need to be carefully designed to prevent them from be...