Goal-directed Markov Decision Process models (GDMDPs) are good models for many decision-theoretic planning tasks. They have been used in conjunction with two different reward stru...
Irregular parallel algorithms pose a significant challenge for achieving high performance because of the difficulty predicting memory access patterns or execution paths. Within an...
The long-term preservation of digitally signed documents may be approached and analyzed from various perspectives, i.e. future data readability, signature validity, storage media ...
We propose a simple probabilistic generative model for image segmentation. Like other probabilistic algorithms (such as EM on a Mixture of Gaussians) the proposed model is princip...
In this paper, image processing and symbol processing are bridged with a common framework. A new computational architecture allows arbitrary fixed images to be used as attractors ...