weka.classifiers.functions.supportVector
Class NormalizedPolyKernel

java.lang.Object
  extended byweka.classifiers.functions.supportVector.Kernel
      extended byweka.classifiers.functions.supportVector.PolyKernel
          extended byweka.classifiers.functions.supportVector.NormalizedPolyKernel
All Implemented Interfaces:
java.io.Serializable

public class NormalizedPolyKernel
extends PolyKernel

The normalized polynomial kernel. K(x,y) = /sqrt() where = PolyKernel(x,y)

Version:
$$
Author:
Eibe Frank (eibe@cs.waikato.ac.nz)
See Also:
Serialized Form

Constructor Summary
NormalizedPolyKernel(Instances dataset, int cacheSize, double exponent, boolean lowerOrder)
          Creates a new NormalizedPolyKernel instance.
 
Method Summary
 double eval(int id1, int id2, Instance inst1)
          Redefines the eval function of PolyKernel.
 
Methods inherited from class weka.classifiers.functions.supportVector.PolyKernel
clean, numEvals
 
Methods inherited from class java.lang.Object
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

NormalizedPolyKernel

public NormalizedPolyKernel(Instances dataset,
                            int cacheSize,
                            double exponent,
                            boolean lowerOrder)
Creates a new NormalizedPolyKernel instance.

Parameters:
dataset - the training dataset used.
cacheSize - the size of the cache (a prime number)
Method Detail

eval

public double eval(int id1,
                   int id2,
                   Instance inst1)
            throws java.lang.Exception
Redefines the eval function of PolyKernel.

Overrides:
eval in class PolyKernel
Throws:
java.lang.Exception