org.openimaj.ml.linear.learner.perceptron

Class OISVM

java.lang.Object

org.openimaj.ml.linear.learner.perceptron.OISVM

All Implemented Interfaces:

OnlineLearner<double[],PerceptronClass>

@References(references=@Reference(type=Article,author={"Francesco Orabona","Claudio Castellini","Barbara Caputo","Luo Jie","Giulio Sandini"},title="On-line independent support vector machines",year="2010",journal="Pattern Recognition",pages={"1402","1412"},number="4",volume="43"))
public class OISVM
extends Object
implements OnlineLearner<double[],PerceptronClass>

Author:

Sina Samangooei (ss@ecs.soton.ac.uk)

Field Summary

Fields

Modifier and Type	Field and Description
protected gnu.trove.list.array.TIntArrayList	supportIndex
protected List<double[]>	supports

Constructor Summary

Constructors

Constructor and Description
OISVM(Kernel<double[]> kernel, double eta)

Method Summary

Modifier and Type	Method and Description
PerceptronClass	predict(double[] x)
void	process(double[] x, PerceptronClass y)

Methods inherited from class java.lang.Object

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

Field Detail

supports

protected List<double[]> supports

supportIndex

protected gnu.trove.list.array.TIntArrayList supportIndex

Constructor Detail

OISVM

public OISVM(Kernel<double[]> kernel,
             double eta)

Parameters:

kernel -

eta -

Method Detail

process

public void process(double[] x,
                    PerceptronClass y)

Specified by:

process in interface OnlineLearner<double[],PerceptronClass>

predict

public PerceptronClass predict(double[] x)

Specified by:

predict in interface OnlineLearner<double[],PerceptronClass>