Reinforcement techniques have been successfully used to maximise the expected cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used to estim...
Many of today’s web sites contain substantial amounts of client-side code, and consequently, they act more like programs than simple documents. This creates robustness and perfo...
We address the character identification problem in
movies and television videos: assigning names to faces on
the screen. Most prior work on person recognition in video
assumes s...
Timothee Cour, Benjamin Sapp, Akash Nagle, Ben Tas...
Enabling machines to understand emotions and feelings of the human users in their natural language textual input during interaction is a challenging issue in Human Computing. Our w...
Li Zhang, Marco Gillies, John A. Barnden, Robert J...
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...