Many applications in information retrieval, natural language processing, data mining, and related fields require a ranking of instances with respect to a specified criteria as op...
In this work, a new type of collaborative learning activity is proposed in order to enable students to explore and understand information in highly mobile situations. We call this ...
Gustavo Zurita, Nelson Baloian, Pedro Antunes, Fel...
Through the combined efforts of many dedicated researchers across the globe, the “message” of the value of games for learning is starting to be heard in formal education, but ...
In the Markov decision process (MDP) formalization of reinforcement learning, a single adaptive agent interacts with an environment defined by a probabilistic transition function....
An algorithm is presented for online learning of rotations. The proposed algorithm involves matrix exponentiated gradient updates and is motivated by the von Neumann divergence. T...