weka.classifiers.functions.supportVector
Class RBFKernel

java.lang.Object
  weka.classifiers.functions.supportVector.Kernel
      weka.classifiers.functions.supportVector.RBFKernel

All Implemented Interfaces:

java.io.Serializable

public class RBFKernel

extends Kernel

The RBF kernel. K(x, y) = e^-(gamma * ^2)

Version:

$$

Author:

Eibe Frank (eibe@cs.waikato.ac.nz), Shane Legg (shane@intelligenesis.net) (sparse vector code), Stuart Inglis (stuart@reeltwo.com) (sparse vector code), J. Lindgren (jtlindgr{at}cs.helsinki.fi) (RBF kernel)

See Also:

Serialized Form

Field Summary

private int	m_cacheSize The size of the cache (a prime number)
private double	m_gamma Gamma for the RBF kernel.
private int	m_kernelEvals Counts the number of kernel evaluations.
private double[]	m_kernelPrecalc The precalculated dotproducts of
private long[]	m_keys
private int	m_numInsts The number of instance in the dataset
private double[]	m_storage Kernel cache

Fields inherited from class weka.classifiers.functions.supportVector.Kernel

m_data

Constructor Summary

RBFKernel(Instances data, int cacheSize, double gamma)
Constructor.

Method Summary

void	clean() Frees the cache used by the kernel.
private double	dotProd(Instance inst1, Instance inst2) Calculates a dot product between two instances
double	eval(int id1, int id2, Instance inst1) Implements the abstract function of Kernel.
int	numEvals() Returns the number of time Eval has been called.

Methods inherited from class java.lang.Object

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

Field Detail

m_kernelPrecalc

private double[] m_kernelPrecalc

The precalculated dotproducts of

m_kernelEvals

private int m_kernelEvals

Counts the number of kernel evaluations.

m_cacheSize

private int m_cacheSize

The size of the cache (a prime number)

m_storage

private double[] m_storage

Kernel cache

m_keys

private long[] m_keys

m_gamma

private double m_gamma

Gamma for the RBF kernel.

m_numInsts

private int m_numInsts

The number of instance in the dataset

Constructor Detail

RBFKernel

public RBFKernel(Instances data,
                 int cacheSize,
                 double gamma)
          throws java.lang.Exception

Constructor. Initializes m_kernelPrecalc[].

Method Detail

eval

public double eval(int id1,
                   int id2,
                   Instance inst1)
            throws java.lang.Exception

Implements the abstract function of Kernel.

Specified by:

eval in class Kernel

Parameters:

id1 - the index of the first instance in the dataset

id2 - the index of the second instance in the dataset

Returns:

the result of the kernel function

Throws:

java.lang.Exception

dotProd

private double dotProd(Instance inst1,
                       Instance inst2)
                throws java.lang.Exception

Calculates a dot product between two instances

Parameters:

inst1 - the first instance

inst2 - the second instance

Returns:

the dot product of the two instances.

Throws:

java.lang.Exception - if an error occurs

clean

public void clean()

Frees the cache used by the kernel.

Specified by:

clean in class Kernel

numEvals

public int numEvals()

Returns the number of time Eval has been called.

Specified by:

numEvals in class Kernel

Returns:

the number of kernel evaluation.