4544 search results - page 566 / 909 » Reinforcement Learning with Time |
158
click to vote
CF
2007
ACM
15 years 10 months ago
2007
ACM
Performance tuning is an important and time consuming task which may have to be repeated for each new application and platform. Although iterative optimisation can automate this p...
203
click to vote
ASC
2008
15 years 6 months ago
2008
Most data mining algorithms assume static behavior of the incoming data. In the real world, the situation is different and most continuously collected data streams are generated by...
279
click to vote
CVPR
2007
IEEE
16 years 8 months ago
2007
IEEE
Traditional methods for creating classifiers have two main disadvantages. Firstly, it is time consuming to acquire, or manually annotate, the training collection. Secondly, the da...
180
click to vote
ICCV
1998
IEEE
16 years 8 months ago
1998
IEEE
Existing object tracking algorithms generally use some form of local optimisation, assuming that an object's position and shape change smoothly over time. In some situations ...
179
Voted
ICML
2009
IEEE
16 years 7 months ago
2009
IEEE
We consider a sequential decision problem where the rewards are generated by a piecewise-stationary distribution. However, the different reward distributions are unknown and may c...