1 In the classic educational context, observing and identifying learner's emotional response allow the teacher to adapt the lesson, with the aim of improving the quality of th...
In this paper, we address two issues of long-standing interest in the reinforcement learning literature. First, what kinds of performance guarantees can be made for Q-learning aft...
The detection of people is one of the foremost problems for indexing, browsing and retrieval of video. The main difficulty is the large appearance variations caused by action, clot...
Recently, mining data streams with concept drifts for actionable insights has become an important and challenging task for a wide range of applications including credit card fraud...
The control of robot swarming in a distributed manner is a difficult problem because global behaviors must emerge as a result of many local actions. This paper uses a bio-inspired ...
Wei-Min Shen, Peter M. Will, Aram Galstyan, Cheng-...