1227 search results - page 49 / 246 » Learning Rates for Q-Learning |
COLT
2008
Springer
14 years 11 months ago
2008
Springer
Standard no-internal-regret (NIR) algorithms compute a fixed point of a matrix, and hence typically require O(n3 ) run time per round of learning, where n is the dimensionality of...
CVPR
2005
IEEE
15 years 11 months ago
2005
IEEE
: In many computer vision classification problems, both the error and time characterizes the quality of a decision. We show that such problems can be formalized in the framework of...
SPEECH
2008
14 years 9 months ago
2008
Although dialogue systems have been an area of research for decades, finding accurate ways of evaluating different systems is still a very active subfield since many leading metho...
127
click to vote
NIPS
2001
14 years 11 months ago
2001
This paper develops a new approach for extremely fast detection in domains where the distribution of positive and negative examples is highly skewed (e.g. face detection or databa...
ECML
2005
Springer
15 years 3 months ago
2005
Springer
This paper argues that severe class imbalance is not just an interesting technical challenge that improved learning algorithms will address, it is much more serious. To be useful, ...