90 search results - page 11 / 18 » Semi-Supervised Learning with Very Few Labeled Training Exam... |
IUI
2000
ACM
13 years 11 months ago
2000
ACM
For intelligent interfaces attempting to learn a user’s interests, the cost of obtaining labeled training instances is prohibitive because the user must directly label each trai...
MICAI
2007
Springer
14 years 1 months ago
2007
Springer
A problem of supervised approaches for text classification is that they commonly require high-quality training data to construct an accurate classifier. Unfortunately, in many real...
MICCAI
2005
Springer
14 years 8 months ago
2005
Springer
Abstract. In this paper, we propose a new dynamic learning framework that requires a small amount of labeled data in the beginning, then incrementally discovers informative unlabel...
ICCV
2009
IEEE
15 years 8 days ago
2009
IEEE
Similarity metrics that are learned from labeled training
data can be advantageous in terms of performance
and/or efficiency. These learned metrics can then be used
in conjuncti...
AAAI
2008
13 years 9 months ago
2008
We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or...