fr.lip6.jkernelmachines.classifier

Class DoubleLLSVM

java.lang.Object

fr.lip6.jkernelmachines.classifier.DoubleLLSVM

All Implemented Interfaces:

Classifier<double[]>, java.lang.Cloneable

public class DoubleLLSVM
extends java.lang.Object
implements Classifier<double[]>

Locally Linear SVM, as described in:
Locally Linear Support Vector Machines
L'ubor Ladicky, Philip H.S. Torr
Procedings of the 28th ICML, Bellevue, WA, USA, 2011.

Author:

picard

Constructor Summary

Constructors

Constructor and Description
DoubleLLSVM()

Method Summary

Modifier and Type	Method and Description
Classifier<double[]>	copy() Creates and returns a copy of this object.
double[]	getB() Return the model biases
double	getC() Returns the hyperparameter C for the hinge loss tradeoff
int	getE() Returns the number of epochs for training
int	getK() return the number of anchor points
int	getNn() Returns the number of anchor points taken into account by the model
double[][]	getW() Return the model hyperplanes
void	setC(double c) Sets the hyperparameter C for the hinge loss tradeoff
void	setE(int e) Sets the number of epochs for training
void	setK(int k) Sets the number of anchor points
void	setNn(int nn) Sets the number of anchor points taken into account by the model
void	train(java.util.List<TrainingSample<double[]>> l) Replace the current training list and train the classifier
double	valueOf(double[] e) Computes the category of the provided example

Methods inherited from class java.lang.Object

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

Constructor Detail

DoubleLLSVM

public DoubleLLSVM()

Method Detail

train

public void train(java.util.List<TrainingSample<double[]>> l)

Description copied from interface: Classifier

Replace the current training list and train the classifier

Specified by:

train in interface Classifier<double[]>

Parameters:

l - list of training samples

valueOf

public double valueOf(double[] e)

Description copied from interface: Classifier

Computes the category of the provided example

Specified by:

valueOf in interface Classifier<double[]>

Parameters:

e - example

Returns:

>0. if e belongs to the category, <0. if not.

copy

public Classifier<double[]> copy()
                          throws java.lang.CloneNotSupportedException

Description copied from interface: Classifier

Creates and returns a copy of this object.

Specified by:

copy in interface Classifier<double[]>

Throws:

java.lang.CloneNotSupportedException

See Also:

Object.clone()

getK

public int getK()

return the number of anchor points

Returns:

the number of anchor points

setK

public void setK(int k)

Sets the number of anchor points

Parameters:

k - the number of anchor points

getE

public int getE()

Returns the number of epochs for training

Returns:

the number of epochs

setE

public void setE(int e)

Sets the number of epochs for training

Parameters:

e - the number of epochs

getC

public double getC()

Returns the hyperparameter C for the hinge loss tradeoff

Returns:

C

setC

public void setC(double c)

Sets the hyperparameter C for the hinge loss tradeoff

Parameters:

c -

getNn

public int getNn()

Returns the number of anchor points taken into account by the model

Returns:

the number of anchor points

setNn

public void setNn(int nn)

Sets the number of anchor points taken into account by the model

Parameters:

nn - the number of anchor opints

getW

public double[][] getW()

Return the model hyperplanes

Returns:

W

getB

public double[] getB()

Return the model biases

Returns:

b