Choosing multiple parameters for support vector machines

Machine Learning

Volumn 46, Issue 1-3, 2002, Pages 131-159

  Chapelle, Olivier ^a   Vapnik, Vladimir ^b   Bousquet, Olivier ^c   Mukherjee, Sayan ^d  

^a UNIVERSITÉ PIERRE ET MARIE CURIE   (France)

^b AT AND T LABS RESEARCH   (United States)

^c ECOLE POLYTECHNIQUE   (France)

^d MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Feature selection; Gradient descent; Kernel selection; Leave one out procedure; Support vector machines

Indexed keywords

FEATURE EXTRACTION; LEARNING ALGORITHMS; PARAMETER ESTIMATION; VECTORS;

GRADIENT DESCENT ALGORITHM; KERNEL SELECTION; SUPPORT VECTOR MACHINES;

LEARNING SYSTEMS;

EID: 0036161011     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1012450327387     Document Type: Article

References (22)

1. Gradient-based optimization of hyper-parameters
2. Model selection for support vector machines
3. Support vector networks
4. Dynamically adapting kernels in support vector machines
5. Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring
6. Face detection in still gray images
7. Probabilistic kernel regression models
8. Estimating the generalization performance of a svm efficiently
9. Adaptive regularization in neural network modeling
10. On estimation of characters obtained in statistical procedure of recognition
11. Gaussian processes and svm: Mean field and leave-one-out
12. Probabilities for support vector machines
13. Soft margins for AdaBoost
14. Feature selection for face detection
15. Bounds on error expectation for support vector machines
16. Generalized approximate crossvalidation for support vector machines: Another way to look at marginlike quantities
17. Feature selection for support vector machines