edu.cmu.minorthird.classify.algorithms.linear
Class KernelVotedPerceptron

java.lang.Object
  edu.cmu.minorthird.classify.OnlineClassifierLearner
      edu.cmu.minorthird.classify.OnlineBinaryClassifierLearner
          edu.cmu.minorthird.classify.algorithms.linear.KernelVotedPerceptron

All Implemented Interfaces:

BinaryClassifierLearner, ClassifierLearner, java.io.Serializable, java.lang.Cloneable

public class KernelVotedPerceptron
extends OnlineBinaryClassifierLearner
implements java.io.Serializable

Voted perceptron algorithm. As described in "Large Margin Classification Using the Perceptron Algorithm", Yoav Freund and Robert E. Schapire, Proceedings of the Eleventh Annual Conference on Computational Learning Theory, 1998. Polynomial kernel is implemented: K(x,y) = (coef0+gamma*)^d Both "voted" and "averaged" modes are implemented (unnormalized). Poly degree = 0 means that no kernel is used. Therefore, mode "averaged" with degree=0 should be equivalent to results in VotedPerceptron.java (file with a faster implementation of the averaged nonnormalized perceptron)

Author:

Vitor Carvalho

See Also:

Serialized Form

Nested Class Summary

class

KernelVotedPerceptron.MyClassifier

Constructor Summary

KernelVotedPerceptron()
Default Constructor: degree=3 and mode="voted"

KernelVotedPerceptron(int degree, java.lang.String mode)
Constructor: specifies degree of poly kernel and mode Example KernelVotedPerceptron(3,"averaged") or (5,"voted")

Method Summary

void	addExample(Example example) Subclasses should use this method to perform whatever incremental update is needed after in response to a new example.
Classifier	getClassifier() Subclasses should use this method to return the current classifier.
void	reset() 'forget' everything about the last learning task, and start a new task.
void	setKernel(int d) set degree of poly kernel K(x,y) = (coef0+ gamma*)^d if set to 0, usual crossproduct is used.
void	setModeAveraged()
void	setModeVoted()
void	setPolyKernelParams(double coef0, double gamma) set params of poly kernel K(x,y) = (coef0+ gamma*)^d
void	setSpeedUp() Set speed-up: use only last 300 support vectors in testing
java.lang.String	toString()

Methods inherited from class edu.cmu.minorthird.classify.OnlineBinaryClassifierLearner

getBinaryClassifier, getSchema, setSchema

Methods inherited from class edu.cmu.minorthird.classify.OnlineClassifierLearner

completeTraining, copy, hasNextQuery, nextQuery, setInstancePool

Methods inherited from class java.lang.Object

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

Methods inherited from interface edu.cmu.minorthird.classify.ClassifierLearner

completeTraining, copy, hasNextQuery, nextQuery, setInstancePool

Constructor Detail

KernelVotedPerceptron

public KernelVotedPerceptron(int degree,
                             java.lang.String mode)

Constructor: specifies degree of poly kernel and mode Example KernelVotedPerceptron(3,"averaged") or (5,"voted")

Parameters:

degree -

mode -

KernelVotedPerceptron

public KernelVotedPerceptron()

Default Constructor: degree=3 and mode="voted"

Method Detail

setKernel

public void setKernel(int d)

set degree of poly kernel K(x,y) = (coef0+ gamma*)^d if set to 0, usual crossproduct is used.

Parameters:

d -

setPolyKernelParams

public void setPolyKernelParams(double coef0,
                                double gamma)

set params of poly kernel K(x,y) = (coef0+ gamma*)^d

Parameters:

coef0 -

gamma -

reset

public void reset()

Description copied from class: OnlineClassifierLearner

'forget' everything about the last learning task, and start a new task. Subclasses need to implement this method

Specified by:

reset in interface ClassifierLearner

Specified by:

reset in class OnlineClassifierLearner

setModeVoted

public void setModeVoted()

setModeAveraged

public void setModeAveraged()

setSpeedUp

public void setSpeedUp()

Set speed-up: use only last 300 support vectors in testing

addExample

public void addExample(Example example)

Description copied from class: OnlineClassifierLearner

Subclasses should use this method to perform whatever incremental update is needed after in response to a new example.

Specified by:

addExample in interface ClassifierLearner

Specified by:

addExample in class OnlineClassifierLearner

getClassifier

public Classifier getClassifier()

Description copied from class: OnlineClassifierLearner

Subclasses should use this method to return the current classifier.

Specified by:

getClassifier in interface ClassifierLearner

Specified by:

getClassifier in class OnlineClassifierLearner

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object