3718 search results - page 293 / 744 » On learning with dissimilarity functions |
168
click to vote
PAKDD
2004
ACM
16 years 1 days ago
2004
ACM
The use of unlabeled data to aid classification is important as labeled data is often available in limited quantity. Instead of utilizing training samples directly into semi-super...
220
click to vote
ECML
2007
Springer
15 years 10 months ago
2007
Springer
Abstract. We present a new reinforcement learning approach for deterministic continuous control problems in environments with unknown, arbitrary reward functions. The difficulty of...
197
click to vote
CVPR
2006
IEEE
15 years 10 months ago
2006
IEEE
In region-based image annotation, keywords are usually associated with images instead of individual regions in the training data set. This poses a major challenge for any learning...
189
click to vote
ICML
1994
IEEE
15 years 10 months ago
1994
IEEE
In the Markov decision process (MDP) formalization of reinforcement learning, a single adaptive agent interacts with an environment defined by a probabilistic transition function....
208
click to vote
NIPS
2008
15 years 8 months ago
2008
Actor-critic algorithms for reinforcement learning are achieving renewed popularity due to their good convergence properties in situations where other approaches often fail (e.g.,...