Sciweavers

167 search results - page 26 / 34
» Effective multi-label active learning for text classificatio...
Sort
View
CORR
2010
Springer
150views Education» more  CORR 2010»
13 years 7 months ago
Extraction of Symbolic Rules from Artificial Neural Networks
Although backpropagation ANNs generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions c...
S. M. Kamruzzaman, Md. Monirul Islam
TEI
2010
ACM
163views Hardware» more  TEI 2010»
14 years 2 months ago
Action and representation in tangible systems: implications for design of learning interactions
In tangible learning systems, the facility to promote physically active engagement highlights the need to understand how different designs impact on action and interaction, and th...
Sara Price, Jennifer G. Sheridan, Taciana Pontual ...
IPMI
2011
Springer
12 years 11 months ago
Generalized Sparse Regularization with Application to fMRI Brain Decoding
Many current medical image analysis problems involve learning thousands or even millions of model parameters from extremely few samples. Employing sparse models provides an effecti...
Bernard Ng, Rafeef Abugharbieh
AAAI
2010
13 years 9 months ago
Community-Guided Learning: Exploiting Mobile Sensor Users to Model Human Behavior
Modeling human behavior requires vast quantities of accurately labeled training data, but for ubiquitous people-aware applications such data is rarely attainable. Even researchers...
Daniel Peebles, Hong Lu, Nicholas D. Lane, Tanzeem...
CVPR
2010
IEEE
14 years 3 months ago
Building and Using a Semantivisual Image Hierarchy
A semantically meaningful image hierarchy can ease the human effort in organizing thousands and millions of pictures (e.g., personal albums), and help to improve performance of en...
Li-Jia Li, Chong Wang, Yongwhan Lim, David Blei, L...