Uses of Class
pt.tumba.ngram.svm.SVMProblem

Packages that use SVMProblem

pt.tumba.ngram.svm

Implementation of Support Vector Machines classification and regression that can be used to categorize text files using N-Grams as features.

Uses of SVMProblem in pt.tumba.ngram.svm

Fields in pt.tumba.ngram.svm declared as SVMProblem

protected SVMProblem

SVMCategorizer.prob

Methods in pt.tumba.ngram.svm with parameters of type SVMProblem

private static void	SVM.solveCSVC(SVMProblem prob, SVMParameter param, double[] alpha, Solver.SolutionInfo si, double Cp, double Cn) Solve the C-Support Vector classification problem.
private static void	SVM.solveEpsilonSVR(SVMProblem prob, SVMParameter param, double[] alpha, Solver.SolutionInfo si) Solve the Epsilon-Support Vector Regression Problem
private static void	SVM.solveNUSVC(SVMProblem prob, SVMParameter param, double[] alpha, Solver.SolutionInfo si) Solve the Nu-Support Vector Classification problem.
private static void	SVM.solveNUSVR(SVMProblem prob, SVMParameter param, double[] alpha, Solver.SolutionInfo si) Solve the Nu-Support Vector Regression Problem
private static void	SVM.solveOneClass(SVMProblem prob, SVMParameter param, double[] alpha, Solver.SolutionInfo si) Solve the SVM Distribution Estimation Problem.
private static void	SVM.svmBinarySVCProbability(SVMProblem prob, SVMParameter param, double Cp, double Cn, double[] probAB) Cross-validation decision values for probability estimates.
static java.lang.String	SVM.svmCheckParameter(SVMProblem prob, SVMParameter param) Check the parameters given to an SVM problem.
static void	SVM.svmCrossValidation(SVMProblem prob, SVMParameter param, int nr_fold, double[] target) Perform cross validation
private static double	SVM.svmSVRProbability(SVMProblem prob, SVMParameter param) Return parameter of a Laplace distribution
static SVMModel	SVM.svmTrain(SVMProblem prob, SVMParameter param) Train the SVM.
(package private) static SVM.decisionFunction	SVM.svmTrainOne(SVMProblem prob, SVMParameter param, double Cp, double Cn) Computation for one step of the training procedure.

Constructors in pt.tumba.ngram.svm with parameters of type SVMProblem

ONECLASSQ(SVMProblem prob, SVMParameter param)

SVCQ(SVMProblem prob, SVMParameter param, byte[] y_)

SVRQ(SVMProblem prob, SVMParameter param)