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...
A standard fMRI experiment is structured around the assumption that onset of relevant neural activity occurs almost immediately after external stimulus. Introducing deliberate len...
Victor Solo, Ben Cassidy, Christopher J. Long, Car...
Dynamic plan execution strategies allow an autonomous agent to respond to uncertainties while improving robustness and reducing the need for an overly conservative plan. Executive...
Patrick R. Conrad, Julie A. Shah, Brian C. William...
We present a novel framework for recognizing repetitive
sequential events performed by human actors with strong
temporal dependencies and potential parallel overlap. Our
solutio...
New Zernike velocity moments have been developed to describe an object, not only by its shape , but also by its motion throughout an image sequence. These are an extended form of ...