384 search results - page 31 / 77 » Temporal Development Methods for Agent-Based |
ML
1998
ACM
13 years 8 months ago
1998
ACM
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...
ICASSP
2011
IEEE
13 years 10 days ago
2011
IEEE
A standard fMRI experiment is structured around the assumption that onset of relevant neural activity occurs almost immediately after external stimulus. Introducing deliberate len...
AIPS
2009
13 years 9 months ago
2009
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...
CVPR
2009
IEEE
15 years 3 months ago
2009
IEEE
We present a novel framework for recognizing repetitive
sequential events performed by human actors with strong
temporal dependencies and potential parallel overlap. Our
solutio...
BMVC
2001
13 years 11 months ago
2001
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 ...