Package org.biojava.stats.svm
Class SigmoidKernel
- java.lang.Object
-
- org.biojava.stats.svm.SigmoidKernel
-
- All Implemented Interfaces:
SVMKernel
public class SigmoidKernel extends 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 Description SigmoidKernel()
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description doubleevaluate(Object a, Object b)Return the dot product of two vectors in an arbitrary feature space.doublegetConstant()doublegetMultiplier()SVMKernelgetWrappedKernel()voidsetConstant(double c)voidsetMultiplier(double m)voidsetWrappedKernel(SVMKernel kernel)doubletanh(double a)StringtoString()
-
-
-
Constructor Detail
-
SigmoidKernel
public SigmoidKernel()
-
-
Method Detail
-
evaluate
public double evaluate(Object a, Object b)
Description copied from interface:SVMKernelReturn the dot product of two vectors in an arbitrary feature space. In this implementation, the `vectors' can actually be arbitrary objects.
-
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)
-
tanh
public double tanh(double a)
-
-