For many problems which would be natural for reinforcement learning, the reward signal is not a single scalar value but has multiple scalar components. Examples of such problems i...
We study the problem of anonymizing data with quasi-sensitive attributes. Quasi-sensitive attributes are not sensitive by themselves, but certain values or their combinations may ...
The computer aided diagnosis (CAD) problems of detecting
potentially diseased structures from medical images are
typically distinguished by the following challenging characterist...
“Client Services”, “User Services”, “Customer Service”: whatever we call it at our various colleges and universities, it’s not just about fixing hardware and softwar...
Gene expression profiles with clinical outcome data enable monitoring of disease progression and prediction of patient survival at the molecular level. We present a new computatio...