smile.classification

Class SVM.Trainer<T>

java.lang.Object

smile.classification.ClassifierTrainer<T>

smile.classification.SVM.Trainer<T>

Enclosing class:

SVM<T>

public static class SVM.Trainer<T>
extends ClassifierTrainer<T>

Trainer for support vector machines.

Constructor Summary

Constructors

Constructor and Description
Trainer(smile.math.kernel.MercerKernel<T> kernel, double C) Constructor of trainer for binary SVMs.
Trainer(smile.math.kernel.MercerKernel<T> kernel, double Cp, double Cn) Constructor of trainer for binary SVMs.
Trainer(smile.math.kernel.MercerKernel<T> kernel, double C, double[] weight, SVM.Multiclass strategy) Constructor of trainer for multi-class SVMs.
Trainer(smile.math.kernel.MercerKernel<T> kernel, double C, int k, SVM.Multiclass strategy) Constructor of trainer for multi-class SVMs.

Method Summary

Modifier and Type	Method and Description
SVM.Trainer<T>	setNumEpochs(int epochs) Sets the number of epochs of stochastic learning.
SVM.Trainer<T>	setTolerance(double tol) Sets the tolerance of convergence test.
SVM<T>	train(T[] x, int[] y) Learns a classifier with given training data.
SVM<T>	train(T[] x, int[] y, double[] weight) Learns a SVM classifier with given training data.

Methods inherited from class smile.classification.ClassifierTrainer

setAttributes

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

Trainer

public Trainer(smile.math.kernel.MercerKernel<T> kernel,
               double C)

Constructor of trainer for binary SVMs.

Parameters:

kernel - the kernel function.

C - the soft margin penalty parameter.

Trainer

public Trainer(smile.math.kernel.MercerKernel<T> kernel,
               double Cp,
               double Cn)

Constructor of trainer for binary SVMs.

Parameters:

kernel - the kernel function.

Cp - the soft margin penalty parameter for positive instances.

Cn - the soft margin penalty parameter for negative instances.

Trainer

public Trainer(smile.math.kernel.MercerKernel<T> kernel,
               double C,
               int k,
               SVM.Multiclass strategy)

Constructor of trainer for multi-class SVMs.

Parameters:

kernel - the kernel function.

C - the soft margin penalty parameter.

k - the number of classes.

Trainer

public Trainer(smile.math.kernel.MercerKernel<T> kernel,
               double C,
               double[] weight,
               SVM.Multiclass strategy)

Constructor of trainer for multi-class SVMs.

Parameters:

kernel - the kernel function.

C - the soft margin penalty parameter.

weight - class weight. Must be positive. The soft margin penalty of class i will be weight[i] * C.

Method Detail

setTolerance

public SVM.Trainer<T> setTolerance(double tol)

Sets the tolerance of convergence test.

Parameters:

tol - the tolerance of convergence test.

setNumEpochs

public SVM.Trainer<T> setNumEpochs(int epochs)

Sets the number of epochs of stochastic learning.

Parameters:

epochs - the number of epochs of stochastic learning.

train

public SVM<T> train(T[] x,
                    int[] y)

Description copied from class: ClassifierTrainer

Learns a classifier with given training data.

Specified by:

train in class ClassifierTrainer<T>

Parameters:

x - the training instances.

y - the training labels.

Returns:

a trained classifier.

train

public SVM<T> train(T[] x,
                    int[] y,
                    double[] weight)

Learns a SVM classifier with given training data.

Parameters:

x - training instances.

y - training labels in [0, k), where k is the number of classes.

weight - instance weight. Must be positive. The soft margin penalty for instance i will be weight[i] * C.

Returns:

trained SVM classifier