Sciweavers

598 search results - page 66 / 120
» Knowledge-Driven Learning and Discovery
Sort
View
AAAI
2008
14 years 5 days ago
Zero-data Learning of New Tasks
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...
Hugo Larochelle, Dumitru Erhan, Yoshua Bengio
KDD
2007
ACM
189views Data Mining» more  KDD 2007»
14 years 10 months ago
Corroborate and learn facts from the web
The web contains lots of interesting factual information about entities, such as celebrities, movies or products. This paper describes a robust bootstrapping approach to corrobora...
Shubin Zhao, Jonathan Betz
ICCV
2005
IEEE
14 years 3 months ago
LOCUS: Learning Object Classes with Unsupervised Segmentation
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
John M. Winn, Nebojsa Jojic
JIIS
2008
89views more  JIIS 2008»
13 years 9 months ago
A note on phase transitions and computational pitfalls of learning from sequences
An ever greater range of applications call for learning from sequences. Grammar induction is one prominent tool for sequence learning, it is therefore important to know its proper...
Antoine Cornuéjols, Michèle Sebag
SDM
2009
SIAM
112views Data Mining» more  SDM 2009»
14 years 7 months ago
A Re-evaluation of the Over-Searching Phenomenon in Inductive Rule Learning.
Most commonly used inductive rule learning algorithms employ a hill-climbing search, whereas local pattern discovery algorithms employ exhaustive search. In this paper, we evaluat...
Frederik Janssen, Johannes Fürnkranz