This study investigated the extent to which the social constructivist approach can be applied to the teaching/learning of translation strategies in an e-learning environment. To a...
Reinforcement learning is a popular and successful framework for many agent-related problems because only limited environmental feedback is necessary for learning. While many algo...
As data streams are gaining prominence in a growing number of emerging application domains, classification on data streams is becoming an active research area. Currently, the typi...
Hotkeys are extremely useful in leveraging expert performance, but learning them is a slow process. This paper investigates alternative menu designs that can motivate and help use...
Tovi Grossman, Pierre Dragicevic, Ravin Balakrishn...
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...