org.biojava.stats.svm

Class SigmoidKernel

java.lang.Object

org.biojava.stats.svm.SigmoidKernel

All Implemented Interfaces:

SVMKernel

public class SigmoidKernel
extends java.lang.Object
implements SVMKernel

This kernel implements a three layer neural net. This is calculated as: tanh(a*k(x,y)+c)

Author:

Matthew Pocock

Constructor Summary

Constructors

Constructor and Description
SigmoidKernel()

Method Summary

Methods

Modifier and Type	Method and Description
double	evaluate(java.lang.Object a, java.lang.Object b) Return the dot product of two vectors in an arbitrary feature space.
double	getConstant()
double	getMultiplier()
SVMKernel	getWrappedKernel()
void	setConstant(double c)
void	setMultiplier(double m)
void	setWrappedKernel(SVMKernel kernel)
double	tanh(double a)
java.lang.String	toString()

Methods inherited from class java.lang.Object

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

Constructor Detail

SigmoidKernel

public SigmoidKernel()

Method Detail

evaluate

public double evaluate(java.lang.Object a,
              java.lang.Object b)

Description copied from interface: SVMKernel

Return the dot product of two vectors in an arbitrary feature space. In this implementation, the `vectors' can actually be arbitrary objects.

Specified by:

evaluate in interface SVMKernel

getConstant

public double getConstant()

setConstant

public void setConstant(double c)

getMultiplier

public double getMultiplier()

setMultiplier

public void setMultiplier(double m)

getWrappedKernel

public SVMKernel getWrappedKernel()

setWrappedKernel

public void setWrappedKernel(SVMKernel kernel)

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

tanh

public double tanh(double a)