For hyper-rectangles in Rd Auer et al. [1] proved a PAC bound of O 1 (d + log 1 ) , where and are the accuracy and confidence parameters. It is still an open question whether one...
This paper analyzes the behavior of the XCS classifier system on imbalanced datasets. We show that XCS with standard parameter settings is quite robust to considerable class imbal...
One important challenge in wireless ad hoc networks is to achieve collision free communication. Many MAC layer protocols have been proposed by considering various communication mod...
We consider reinforcement learning in the parameterized setup, where the model is known to belong to a parameterized family of Markov Decision Processes (MDPs). We further impose ...
After a classifier is trained using a machine learning algorithm and put to use in a real world system, it often faces noise which did not appear in the training data. Particularl...