External regret compares the performance of an online algorithm, selecting among N actions, to the performance of the best of those actions in hindsight. Internal regret compares ...
We use the connection between resource-bounded dimension and the online mistake-bound model of learning to show that the following classes have polynomial-time dimension zero.
We present an algorithm for detecting and modeling rhythmic temporal patterns from the record of an individual's computer activity, or online "presence." The model ...
This position paper describes the implementation and initial findings of a game called Personal Investigator (PI). PI is an online 3D detective game that implements a model of Bri...
We consider the problem of learning to predict as well as the best in a group of experts making continuous predictions. We assume the learning algorithm has prior knowledge of the ...