1799 search results - page 332 / 360 » Filtered Reinforcement Learning |
JMLR
2002
13 years 7 months ago
2002
We construct a framework which allows an algorithm to turn the distributions produced by some boosting algorithms into polynomially smooth distributions (w.r.t. the PAC oracle...
IJRR
2010
13 years 6 months ago
2010
This paper presents a novel approach to detect and track pedestrians and cars based on the combined information retrieved from a camera and a laser range scanner. Laser data points...
BMVC
2010
13 years 5 months ago
2010
Off-line trained class-specific object detectors are designed to detect any instance of the class in a given image or video sequence. In the context of object tracking, however, o...
ML
2010
ACM
13 years 2 months ago
2010
ACM
Traditional classification methods assume that the training and the test data arise from the same underlying distribution. However, in several adversarial settings, the test set is...
ICML
2000
IEEE
14 years 8 months ago
2000
IEEE
If all features causing heterogeneity were observed, a mixture of experts approach (Jacobs et al., 1991) is likely to be superior to using a single model. When unobserved or very n...