Sciweavers

6039 search results - page 256 / 1208
» The Function Space of an Activity
Sort
View
IWANN
1999
Springer
15 years 11 months ago
Using Temporal Neighborhoods to Adapt Function Approximators in Reinforcement Learning
To avoid the curse of dimensionality, function approximators are used in reinforcement learning to learn value functions for individual states. In order to make better use of comp...
R. Matthew Kretchmar, Charles W. Anderson
CVPR
2008
IEEE
16 years 9 months ago
Semi-supervised SVM batch mode active learning for image retrieval
Active learning has been shown as a key technique for improving content-based image retrieval (CBIR) performance. Among various methods, support vector machine (SVM) active learni...
Steven C. H. Hoi, Rong Jin, Jianke Zhu, Michael R....
CHI
2008
ACM
16 years 7 months ago
Activity-based prototyping of ubicomp applications for long-lived, everyday human activities
We designed an activity-based prototyping process realized in the ActivityDesigner system that combines the theoretical framework of Activity-Centered Design with traditional iter...
Yang Li, James A. Landay
SIGCOMM
2009
ACM
16 years 1 months ago
Router primitives for programmable active measurement
Active probe-based measurements are the foundation for understanding important network path properties such as SLA compliance and available bandwidth. Well-known challenges in act...
Joel Sommers, Paul Barford, Mark Crovella
BMCBI
2010
183views more  BMCBI 2010»
15 years 7 months ago
Active learning for human protein-protein interaction prediction
Background: Biological processes in cells are carried out by means of protein-protein interactions. Determining whether a pair of proteins interacts by wet-lab experiments is reso...
Thahir P. Mohamed, Jaime G. Carbonell, Madhavi Gan...