In this paper, we propose a unified framework for computing atlases from manually labeled data at various degrees of "sharpness" and the joint registration-segmentation o...
B. T. Thomas Yeo, Mert R. Sabuncu, Rahul Desikan, ...
In many real-world applications, such as image retrieval, it would be natural to measure the distances from one instance to others using instance specific distance which captures ...
We consider the problem of multi-task reinforcement learning, where the agent needs to solve a sequence of Markov Decision Processes (MDPs) chosen randomly from a fixed but unknow...
Aaron Wilson, Alan Fern, Soumya Ray, Prasad Tadepa...
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of ...
Similarity matrices generated from many applications may not be positive semidefinite, and hence can't fit into the kernel machine framework. In this paper, we study the prob...