When two or more agents interacting, their behaviors are not necessarily matching. Automated ways to overcome conicts in the behavior of agents can make the execution of interacti...
An interpretation system finds the likely mappings from portions of an image to real-world objects. An interpretation policy specifies when to apply which imaging operator, to whi...
In order to claim fully general intelligence in an autonomous agent, the ability to learn is one of the most central capabilities. Classical machine learning techniques have had ma...
—Modeling data with linear combinations of a few elements from a learned dictionary has been the focus of much recent research in machine learning, neuroscience, and signal proce...
Labeling faces in news video with their names is an interesting research problem which was previously solved using supervised methods that demand significant user efforts on lab...