354 search results - page 32 / 71 » Learning classifiers from only positive and unlabeled data |
ICDM
2010
IEEE
13 years 6 months ago
2010
IEEE
Active learning has been proven a reliable strategy to reduce manual efforts in training data labeling. Such strategies incorporate the user as oracle: the classifier selects the m...
ICASSP
2009
IEEE
14 years 3 months ago
2009
IEEE
Training accurate acoustic models typically requires a large amount of transcribed data, which can be expensive to obtain. In this paper, we describe a novel semi-supervised learn...
CVPR
2004
IEEE
14 years 10 months ago
2004
IEEE
Object classification in far-field video sequences is a challenging problem because of low resolution imagery and projective image distortion. Most existing far-field classificati...
AAAI
2004
13 years 10 months ago
2004
Traditionally, text classifiers are built from labeled training examples. Labeling is usually done manually by human experts (or the users), which is a labor intensive and time co...
BIBM
2010
IEEE
13 years 6 months ago
2010
IEEE
The emergence of data rich domains has led to an exponential growth in the size and number of data repositories, offering exciting opportunities to learn from the data using machin...