202 search results - page 25 / 41 » How Local Should a Learning Method Be |
119
click to vote
ICML
2010
IEEE
15 years 3 months ago
2010
IEEE
We introduce a novel active learning algorithm for classification of network data. In this setting, training instances are connected by a set of links to form a network, the label...
144
click to vote
AVBPA
2005
Springer
15 years 4 months ago
2005
Springer
There has been a flurry of works on video sequence-based face recognition in recent years. One of the hard problems in this area is how to effectively combine the facial configu...
106
click to vote
MICAI
2009
Springer
15 years 9 months ago
2009
Springer
Reinforcement Learning is a commonly used technique in robotics, however, traditional algorithms are unable to handle large amounts of data coming from the robot’s sensors, requi...
128
click to vote
AAAI
2008
15 years 4 months ago
2008
Transfer learning addresses the problem of how to utilize plenty of labeled data in a source domain to solve related but different problems in a target domain, even when the train...
125
Voted
JSAC
2010
15 years 23 days ago
2010
—Inspired by the biological entities’ ability to achieve reciprocity in the course of evolution, this paper considers a conjecture-based distributed learning approach that enab...