Sciweavers

1351 search results - page 120 / 271
» Learning from compressed observations
Sort
View
ICML
2010
IEEE
15 years 5 months ago
Bayesian Multi-Task Reinforcement Learning
We consider the problem of multi-task reinforcement learning where the learner is provided with a set of tasks, for which only a small number of samples can be generated for any g...
Alessandro Lazaric, Mohammad Ghavamzadeh
FGR
2000
IEEE
114views Biometrics» more  FGR 2000»
15 years 8 months ago
Wide-Range, Person- and Illumination-Insensitive Head Orientation Estimation
We present an algorithm for estimation of head orientation, given cropped images of a subject’s head from any viewpoint. Our algorithm handles dramatic changes in illumination, ...
Ying Wu, Kentaro Toyama
CHI
1996
ACM
15 years 8 months ago
Children's Collaboration Styles in a Newtonian Microworld
TurboTurtle is a animated multi-user microworld that children use to explore concepts in Newtonian physics. It is a groupware system where students, each on their own computer, ca...
Andy Cockburn, Saul Greenberg
ICML
2010
IEEE
15 years 5 months ago
Fast Neighborhood Subgraph Pairwise Distance Kernel
We introduce a novel graph kernel called the Neighborhood Subgraph Pairwise Distance Kernel. The kernel decomposes a graph into all pairs of neighborhood subgraphs of small radius...
Fabrizio Costa, Kurt De Grave
IJVR
2008
127views more  IJVR 2008»
15 years 4 months ago
Embodied Tutors for Interaction Skills Simulation Training
This paper describes intelligent virtual tutors for interaction skills training who can serve the roles of demonstrator, coach, trainer, mentor, and observer. These roles meet the ...
Robert Hubal