Catalano.Statistics.Kernels

Class Cauchy

java.lang.Object

Catalano.Statistics.Kernels.Cauchy

All Implemented Interfaces:

IMercerKernel<double[]>, java.io.Serializable

public class Cauchy
extends java.lang.Object
implements IMercerKernel<double[]>

Cauchy Kernel. The Cauchy kernel comes from the Cauchy distribution (Basak, 2008). It is a long-tailed kernel and can be used to give long-range influence and sensitivity over the high dimension space.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
Cauchy() Constructs a new Cauchy Kernel.
Cauchy(double sigma) Constructs a new Cauchy Kernel.

Method Summary

Modifier and Type	Method and Description
double	Function(double[] x, double[] y) The kernel function.
double	getSigma() Get the kernel's sigma value.
void	setSigma(double sigma) Sets the kernel's sigma value.

Methods inherited from class java.lang.Object

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

Constructor Detail

Cauchy

public Cauchy()

Constructs a new Cauchy Kernel. Default sigma = 1.

Cauchy

public Cauchy(double sigma)

Constructs a new Cauchy Kernel.

Parameters:

sigma - The value for sigma.

Method Detail

getSigma

public double getSigma()

Get the kernel's sigma value.

Returns:

Sigma value.

setSigma

public void setSigma(double sigma)

Sets the kernel's sigma value.

Parameters:

sigma - Sigma value.

Function

public double Function(double[] x,
                       double[] y)

Description copied from interface: IMercerKernel

The kernel function.

Specified by:

Function in interface IMercerKernel<double[]>

Parameters:

x - Vector x in input space.

y - Vector y in input space.

Returns:

Dot product in feature (kernel) space.