Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

IJCNN
2006
IEEE

favoriteEmaildiscussreport

146views Neural Networks» more IJCNN 2006»

Learning the Kernel in Mahalanobis One-Class Support Vector Machines

13 years 10 months ago

Learning the Kernel in Mahalanobis One-Class Support Vector Machines

Download www.cse.ust.hk

— In this paper, we show that one-class SVMs can also utilize data covariance in a robust manner to improve performance. Furthermore, by constraining the desired kernel function as a convex combination of base kernels, we show that the weighting coefﬁcients can be learned via quadratically constrained quadratic programming (QCQP) or second order cone programming (SOCP) methods. Performance on both toy and real-world data sets show promising results. This paper thus offers another demonstration of the synergy between convex optimization and kernel methods.

Ivor W. Tsang, James T. Kwok, Shutao Li

Real-time Traffic

Convex Combination | IJCNN 2006 | Order Cone Programming | Quadratically Constrained Quadratic Programming |

claim paper

Related Content

» Training of Support Vector Machines with Mahalanobis Kernels

» Face Authentication Using OneClass Support Vector Machines

» A Multiple Instance Learning Approach for Content Based Image Retrieval Using OneClass Sup...

» Consistency and Convergence Rates of OneClass SVMs and Related Algorithms

» NonRelevance Feedback Document Retrieval based on One Class SVM and SVDD

» Kernel methods and the exponential family

» Learning Bounds for Support Vector Machines with Learned Kernels

» Fast QueryOptimized Kernel Machine Classification Via Incremental Approximate Nearest Supp...

» Entropy Numbers Operators and Support Vector Kernels

Post Info
More Details (n/a)

Added	11 Jun 2010
Updated	11 Jun 2010
Type	Conference
Year	2006
Where	IJCNN
Authors	Ivor W. Tsang, James T. Kwok, Shutao Li

Comments (0)