A new multi-class SVM based on a uniform convergence result
- 1 January 2000
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 183-188 vol.4
- https://doi.org/10.1109/ijcnn.2000.860770
Abstract
We introduce a support vector machine devoted to the approximation of multi-class discriminant functions. Its training procedure consists in minimizing an expression of the guaranteed risk. This bound is significantly tighter than the former ones, which should make the implementation of the structural risk minimization inductive principle in the context of multi-class discrimination better grounded.Keywords
This publication has 6 references indexed in Scilit:
- The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the networkIEEE Transactions on Information Theory, 1998
- Support-vector networksMachine Learning, 1995
- The Nature of Statistical Learning TheoryPublished by Springer Nature ,1995
- Neural Network Classifiers Estimate Bayesian a posteriori ProbabilitiesNeural Computation, 1991
- Entropy, Compactness and the Approximation of OperatorsPublished by Cambridge University Press (CUP) ,1990
- On the Uniform Convergence of Relative Frequencies of Events to Their ProbabilitiesTheory of Probability and Its Applications, 1971