Sciweavers

949 search results - page 162 / 190
» Fast Self-Recovering Controllers
Sort
View
ICML
1994
IEEE
15 years 3 months ago
A Modular Q-Learning Architecture for Manipulator Task Decomposition
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
Chen K. Tham, Richard W. Prager
96
Voted
BMVC
2002
15 years 2 months ago
Real-time gesture recognition using deterministic boosting
A gesture recognition system which can reliably recognize single-hand gestures in real time on a 600Mhz notebook computer is described. The system has a vocabulary of 46 gestures ...
Raymond Lockton, Andrew W. Fitzgibbon
AVI
2008
15 years 2 months ago
TapTap and MagStick: improving one-handed target acquisition on small touch-screens
We present the design and evaluation of TapTap and MagStick, two thumb interaction techniques for target acquisition on mobile devices with small touch-screens. These two techniqu...
Anne Roudaut, Stéphane Huot, Eric Lecolinet
DBSEC
2008
136views Database» more  DBSEC 2008»
15 years 1 months ago
An Opinion Model for Evaluating Malicious Activities in Pervasive Computing Systems
Pervasive computing applications typically involve cooperation among a number of entities spanning multiple organizations. Any security breach in any single entity can have very fa...
Indrajit Ray, Nayot Poolsappasit, Rinku Dewri
NIPS
2008
15 years 1 months ago
Local Gaussian Process Regression for Real Time Online Model Learning
Learning in real-time applications, e.g., online approximation of the inverse dynamics model for model-based robot control, requires fast online regression techniques. Inspired by...
Duy Nguyen-Tuong, Matthias Seeger, Jan Peters