Sciweavers

779 search results - page 55 / 156
» Two faces of active learning
Sort
View
ICIP
2003
IEEE
14 years 11 months ago
Image compression with on-line and off-line learning
Images typically contain smooth regions, which are easily compressed by linear transforms, and high activity regions (edges, textures), which are harder to compress. To compress t...
Patrice Y. Simard, Christopher J. C. Burges, David...
ICASSP
2008
IEEE
14 years 4 months ago
Learning with noisy supervision for Spoken Language Understanding
Data-driven Spoken Language Understanding (SLU) systems need semantically annotated data which are expensive, time consuming and prone to human errors. Active learning has been su...
Christian Raymond, G. Riccardfi
FUIN
2008
142views more  FUIN 2008»
13 years 10 months ago
Relational Transformation-based Tagging for Activity Recognition
Abstract. The ability to recognize human activities from sensory information is essential for developing the next generation of smart devices. Many human activity recognition tasks...
Niels Landwehr, Bernd Gutmann, Ingo Thon, Luc De R...
ALT
2010
Springer
13 years 11 months ago
Online Multiple Kernel Learning: Algorithms and Mistake Bounds
Online learning and kernel learning are two active research topics in machine learning. Although each of them has been studied extensively, there is a limited effort in addressing ...
Rong Jin, Steven C. H. Hoi, Tianbao Yang
ICML
2009
IEEE
14 years 11 months ago
Deep learning from temporal coherence in video
This work proposes a learning method for deep architectures that takes advantage of sequential data, in particular from the temporal coherence that naturally exists in unlabeled v...
Hossein Mobahi, Ronan Collobert, Jason Weston