RSSL (version 0.9.3)

SVM: SVM Classifier

Description

Support Vector Machine implementation using the quadprog solver.

Usage

SVM(X, y, C = 1, kernel = NULL, scale = TRUE, intercept = FALSE,
  x_center = TRUE, eps = 1e-09)

Arguments

X

matrix; Design matrix for labeled data

y

factor or integer vector; Label vector

C

numeric; Cost variable

kernel

kernlab::kernel to use

scale

logical; Should the features be normalized? (default: FALSE)

intercept

logical; Whether an intercept should be included

x_center

logical; Should the features be centered?

eps

numeric; Small value to ensure positive definiteness of the matrix in the QP formulation

Value

S4 object of type SVM

Details

This implementation will typically be slower and use more memory than the svmlib implementation in the e1071 package. It is, however, useful for comparisons with the TSVM implementation.

See Also

Other RSSL classifiers: EMLeastSquaresClassifier, EMLinearDiscriminantClassifier, GRFClassifier, ICLeastSquaresClassifier, ICLinearDiscriminantClassifier, KernelLeastSquaresClassifier, LaplacianKernelLeastSquaresClassifier(), LaplacianSVM, LeastSquaresClassifier, LinearDiscriminantClassifier, LinearSVM, LinearTSVM(), LogisticLossClassifier, LogisticRegression, MCLinearDiscriminantClassifier, MCNearestMeanClassifier, MCPLDA, MajorityClassClassifier, NearestMeanClassifier, QuadraticDiscriminantClassifier, S4VM, SelfLearning, TSVM, USMLeastSquaresClassifier, WellSVM, svmlin()