Sciweavers

1837 search results - page 176 / 368
» Learning From Ambiguous Examples
Sort
View
144
Voted
ICML
2010
IEEE
15 years 7 months ago
Structured Output Learning with Indirect Supervision
We present a novel approach for structure prediction that addresses the difficulty of obtaining labeled structures for training. We observe that structured output problems often h...
Ming-Wei Chang, Vivek Srikumar, Dan Goldwasser, Da...
JMLR
2010
106views more  JMLR 2010»
15 years 28 days ago
Why Does Unsupervised Pre-training Help Deep Learning?
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
VLDB
2007
ACM
118views Database» more  VLDB 2007»
16 years 6 months ago
Inferring XML Schema Definitions from XML Data
Although the presence of a schema enables many optimizations for operations on XML documents, recent studies have shown that many XML documents in practice either do not refer to ...
Geert Jan Bex, Frank Neven, Stijn Vansummeren
178
Voted
ECCV
1998
Springer
15 years 10 months ago
On Degeneracy of Linear Reconstruction from Three Views: Linear Line Complex and Applications
This paper investigates the linear degeneracies of projective structure estimation from point and line features across three views. We show that the rank of the linear system of e...
Gideon P. Stein, Amnon Shashua
182
Voted
ISWC
2006
IEEE
16 years 5 days ago
Discovering Characteristic Actions from On-Body Sensor Data
We present an approach to activity discovery, the unsupervised identification and modeling of human actions embedded in a larger sensor stream. Activity discovery can be seen as ...
David Minnen, Thad Starner, Irfan A. Essa, Charles...