Back to Search
Start Over
Geometrical Properties of Nu Support Vector Machines with Different Norms.
- Source :
-
Neural Computation . Nov2005, Vol. 17 Issue 11, p2508-2529. 22p. - Publication Year :
- 2005
-
Abstract
- By employing the L1 or L∞ norms in maximizing margins, support vector machines (SVMs) result in a linear programming problem that requires a lower computational load compared to SVMs with the L2 norm. However, how the change of norm affects the generalization ability of SVMs has not been clarified so far except for numerical experiments. In this letter, the geometrical meaning of SVMs with the Lp norm is investigated, and the SVM solutions are shown to have rather little dependency on p. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 08997667
- Volume :
- 17
- Issue :
- 11
- Database :
- Academic Search Index
- Journal :
- Neural Computation
- Publication Type :
- Academic Journal
- Accession number :
- 17980619
- Full Text :
- https://doi.org/10.1162/0899766054796897