I am trying to perform k-fold cross validation with LibSVM's java library.
how far i have understood the cross validation process, the svm_cross_validation() method should give me the optimised values of parameters. Where svm_cross_validation() method doesn't return any value, instead it sets the target class labels of training data in one of the arguments.
Now I am totally confused about how to get the best values of parameters for kernel functions. It would be a great help if someone can elaborate the process of getting the best suitable parameter values performing cross validation with LibSVM's Java library.
If more information is required please comment.
