Developing automated agents that intelligently perform complex real world tasks is time consuming and expensive. The most expensive part of developing these intelligent task perfo...
We introduce the use of learned shaping rewards in reinforcement learning tasks, where an agent uses prior experience on a sequence of tasks to learn a portable predictor that est...
We propose a Bayesian approach to incorporate anatomical information in the clustering of fiber trajectories. An expectationmaximization (EM) algorithm is used to cluster the traj...
DKAL is a new declarative authorization language for distributed systems. It is based on existential fixed-point logic and is considerably more expressive than existing authoriza...
We describe a new method to predict the tertiary structure of new-fold proteins. Our two-phase approach combines the knowledge-based fragmentpacking with the minimization of a phy...
Jinhui Ding, Elizabeth Eskow, Nelson L. Max, Silvi...