This paper describes a novel approach to the semantic relation detection problem. Instead of relying only on the training instances for a new relation, we leverage the knowledge l...
Chang Wang, James Fan, Aditya Kalyanpur, David Gon...
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
It is argued that the analysis of the learner's generated log files during interactions with a learning environment is necessary to produce interpretative views of their activ...
: Using speech input to augment the remote control can be an alternative interaction technique for interactive television. However, little is known about how to design such a syste...
Up-propagation is an algorithm for inverting and learning neural network generative models. Sensory input is processed by inverting a model that generates patterns from hidden var...