TD-Gammon is a neural network that is able to teach itself to play backgammon solely by playing against itself and learning from the results. Starting from random initial play, TD...
Abstract. Learning ranking functions is crucial for solving many problems, ranging from document retrieval to building recommendation systems based on an individual user’s prefer...
We investigate a topic at the interface of machine learning and cognitive science. Human active learning, where learners can actively query the world for information, is contraste...
Rui M. Castro, Charles Kalish, Robert Nowak, Ruich...
In this paper, we propose an evolutionary approach to the design of output codes for multiclass pattern recognition problems. This approach has the advantage of taking into account...
Blogs have the aordance to become an integral part of teaching and learning processes as a vehicle for knowledge management. Open, exible systems integrating blogs provide user-f...