330 search results - page 9 / 66 » Self-taught learning: transfer learning from unlabeled data |
ICML
2007
IEEE
16 years 15 days ago
2007
IEEE
We consider a setting for discriminative semisupervised learning where unlabeled data are used with a generative model to learn effective feature representations for discriminativ...
NIPS
2004
15 years 1 months ago
2004
We consider the semi-supervised learning problem, where a decision rule is to be learned from labeled and unlabeled data. In this framework, we motivate minimum entropy regulariza...
ICCV
2009
IEEE
16 years 4 months ago
2009
IEEE
Labeling image collections is a tedious task, especially
when multiple labels have to be chosen for each image. In
this paper we introduce a new framework that extends state
of ...
131
click to vote
TAL
2010
Springer
14 years 9 months ago
2010
Springer
This paper shows how the best data-driven dependency parsers available today [1] can be improved by learning from unlabeled data. We focus on German and Swedish and show that label...
IJCAI
2003
15 years 1 months ago
2003
This paper summarizes a probabilistic approach for localizing people through the signal strengths of a wireless IEEE 802.11b network. Our approach uses data labeled by ground trut...