Sciweavers

916 search results - page 136 / 184
» Algorithm selection: a quantitative computation-intensive op...
Sort
View
TNN
2010
171views Management» more  TNN 2010»
14 years 8 months ago
Sensitivity versus accuracy in multiclass problems using memetic Pareto evolutionary neural networks
This paper proposes a multiclassification algorithm using multilayer perceptron neural network models. It tries to boost two conflicting main objectives of multiclassifiers: a high...
Juan Carlos Fernández Caballero, Francisco ...
ICML
2008
IEEE
16 years 2 months ago
Localized multiple kernel learning
Recently, instead of selecting a single kernel, multiple kernel learning (MKL) has been proposed which uses a convex combination of kernels, where the weight of each kernel is opt...
Ethem Alpaydin, Mehmet Gönen
ISM
2006
IEEE
92views Multimedia» more  ISM 2006»
15 years 8 months ago
Strategies for Efficient Streaming in Delay-Tolerant Multimedia Applications
We consider Multimedia applications where clients specify a minimum desired stream rate (quality) and a time till when they are willing to wait, termed delay tolerance. The Conten...
Saraswathi Krithivasan, Sridhar Iyer
IJCV
2006
206views more  IJCV 2006»
15 years 1 months ago
Random Sampling for Subspace Face Recognition
Subspacefacerecognitionoftensuffersfromtwoproblems:(1)thetrainingsamplesetissmallcompared with the high dimensional feature vector; (2) the performance is sensitive to the subspace...
Xiaogang Wang, Xiaoou Tang
CVPR
2009
IEEE
16 years 9 months ago
Let the Kernel Figure it Out; Principled Learning of Pre-processing for Kernel Classifiers
Most modern computer vision systems for high-level tasks, such as image classification, object recognition and segmentation, are based on learning algorithms that are able to se...
Peter V. Gehler, Sebastian Nowozin