849 search results - page 79 / 170 » Learning to Solve Problems from Exercises |
CVPR
2008
IEEE
15 years 12 months ago
2008
IEEE
To learn a new visual category from few examples, prior knowledge from unlabeled data as well as previous related categories may be useful. We develop a new method for transfer le...
IJCAI
2007
14 years 11 months ago
2007
Many current state-of-the-art planners rely on forward heuristic search. The success of such search typically depends on heuristic distance-to-the-goal estimates derived from the ...
FOCS
2009
IEEE
14 years 7 months ago
2009
IEEE
We give a new model of learning motivated by smoothed analysis (Spielman and Teng, 2001). In this model, we analyze two new algorithms, for PAC-learning DNFs and agnostically learn...
ECCV
2010
Springer
14 years 10 months ago
2010
Springer
Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
IROS
2006
IEEE
15 years 3 months ago
2006
IEEE
— Navigation is one of the fundamental tasks for a mobile robot. The majority of path planning approaches has been designed to entirely solve the given problem from scratch given...