Empirical comparison of cross-validation and internal metrics for tuning SVM hyperparameters
Authors:
- Edson DuarteEDEdson Duarte
- Jacques WainerJWJacques Wainer
- 1 March 2017
- journal article
- Published by Elsevier in Pattern Recognition Letters
- Vol. 88, 6-11
Abstract
No abstract availableKeywords
This publication has 8 references indexed in Scilit:
- Fully Empirical and Data-Dependent Stability-Based BoundsIEEE Transactions on Cybernetics, 2014
- In-Sample and Out-of-Sample Model Selection and Error Estimation for Support Vector MachinesIEEE Transactions on Neural Networks and Learning Systems, 2012
- Analysis of the Distance Between Two Classes for Tuning SVM HyperparametersIEEE Transactions on Neural Networks, 2010
- Radius Margin Bounds for Support Vector Machines with the RBF KernelNeural Computation, 2003
- Hyperparameter design criteria for support vector classifiersNeurocomputing, 2003
- Evaluation of simple performance measures for tuning SVM hyperparametersNeurocomputing, 2003
- Bounds on Error Expectation for Support Vector MachinesNeural Computation, 2000
- Sample compression, learnability, and the Vapnik-Chervonenkis dimensionMachine Learning, 1995