Domain adaptation is a fundamental learning problem where one wishes to use labeled data from one or several source domains to learn a hypothesis performing well on a different, y...
Mining data streams is important in both science and commerce. Two major challenges are (1) the data may grow without limit so that it is difficult to retain a long history; and (...
Intelligent planning algorithms such as the Partially Observable Markov Decision Process (POMDP) have succeeded in dialog management applications [10, 11, 12] because of their rob...
Selective sampling is a form of active learning which can reduce the cost of training by only drawing informative data points into the training set. This selected training set is ...
Zhenyu Lu, Anand I. Rughani, Bruce I. Tranmer, Jos...
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...