243 search results - page 16 / 49 » Learning Abstraction Hierarchies for Problem Solving |
EUROCOLT
1999
Springer
14 years 27 days ago
1999
Springer
Abstract. Recent works have shown the advantage of using Active Learning methods, such as the Query by Committee (QBC) algorithm, to various learning problems. This class of Algori...
ECML
2005
Springer
14 years 2 months ago
2005
Springer
Abstract. Classical planning domain representations assume all the objects from one type are exactly the same. But when solving problems in the real world systems, the execution of...
ML
2008
ACM
13 years 8 months ago
2008
ACM
Abstract. We consider a large volume principle for transductive learning that prioritizes the transductive equivalence classes according to the volume they occupy in hypothesis spa...
ICML
2004
IEEE
14 years 9 months ago
2004
IEEE
Reinforcement learning deals with learning optimal or near optimal policies while interacting with the environment. Application domains with many continuous variables are difficul...
PPSN
2004
Springer
14 years 2 months ago
2004
Springer
Abstract. A key problem in designing artificial neural networks for visual object recognition tasks is the proper choice of the network architecture. Evolutionary optimization met...