We present a new algorithm, called incremental least squares policy iteration (ILSPI), for finding the infinite-horizon stationary policy for partially observable Markov decision ...
Abstract. This paper presents an online learning algorithm for appearancebased gaze estimation that allows free head movement in a casual desktop environment. Our method avoids the...
Current semi-supervised incremental learning approaches select unlabeled examples with predicted high confidence for model re-training. We show that for many applications this dat...
Developing a distributed application is hard due to the complexity inherent to distributed communication. Moreover, distributed object communication technology is always changing,...
Much of the elegance and power of Smalltalk comes from its programming environment and tools. First introduced more than 20 years ago, the Smalltalk browser enables programmers to...