Sciweavers

4660 search results - page 410 / 932
» Learning from imperfect data
Sort
View
ICAI
2009
15 years 4 months ago
Learning Mappings with Neural Network
The authors extended the idea of training multiple tasks simultaneously on a partially shared feed forward network. A shared input subvector was added to represented common inputs...
Yefei Peng, Paul W. Munro
ICANN
2009
Springer
15 years 4 months ago
MINLIP: Efficient Learning of Transformation Models
Abstract. This paper studies a risk minimization approach to estimate a transformation model from noisy observations. It is argued that transformation models are a natural candidat...
Vanya Van Belle, Kristiaan Pelckmans, Johan A. K. ...
CORR
2011
Springer
182views Education» more  CORR 2011»
14 years 10 months ago
Adaptively Learning the Crowd Kernel
We introduce an algorithm that, given n objects, learns a similarity matrix over all n2 pairs, from crowdsourced data alone. The algorithm samples responses to adaptively chosen t...
Omer Tamuz, Ce Liu, Serge Belongie, Ohad Shamir, A...
SEMWEB
2009
Springer
16 years 1 months ago
Learning to Map Ontologies with Neural Network
In this paper the authors applied the idea of training multiple tasks simultaneously on a partially shared feed forward network to domain of ontology mapping. A “cross trainingâ€...
Yefei Peng, Paul W. Munro, Ming Mao
CVPR
2008
IEEE
16 years 1 months ago
Fast kernel learning for spatial pyramid matching
Spatial pyramid matching (SPM) is a simple yet effective approach to compute similarity between images. Similarity kernels at different regions and scales are usually fused by som...
Junfeng He, Shih-Fu Chang, Lexing Xie