Sciweavers

1380 search results - page 30 / 276
» On Universal Transfer Learning
Sort
View
PKDD
2009
Springer
148views Data Mining» more  PKDD 2009»
14 years 3 months ago
Feature Selection by Transfer Learning with Linear Regularized Models
Abstract. This paper presents a novel feature selection method for classification of high dimensional data, such as those produced by microarrays. It includes a partial supervisio...
Thibault Helleputte, Pierre Dupont
ACL
2009
13 years 6 months ago
Multi-Task Transfer Learning for Weakly-Supervised Relation Extraction
Creating labeled training data for relation extraction is expensive. In this paper, we study relation extraction in a special weakly-supervised setting when we have only a few see...
Jing Jiang
ACCV
2010
Springer
13 years 3 months ago
Interactive Event Search through Transfer Learning
Activity videos are widespread on the Internet but current video search is limited to text tags due to limitations in recognition systems. One of the main reasons for this limitati...
Antony Lam, Amit K. Roy Chowdhury, Christian R. Sh...
ECCV
2008
Springer
14 years 10 months ago
Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks
Abstract. Building visual recognition models that adapt across different domains is a challenging task for computer vision. While feature-learning machines in the form of hierarchi...
Amr Ahmed, Kai Yu, Wei Xu, Yihong Gong, Eric P. Xi...
ICML
2008
IEEE
14 years 9 months ago
Automatic discovery and transfer of MAXQ hierarchies
We present an algorithm, HI-MAT (Hierarchy Induction via Models And Trajectories), that discovers MAXQ task hierarchies by applying dynamic Bayesian network models to a successful...
Neville Mehta, Soumya Ray, Prasad Tadepalli, Thoma...