Package elki.similarity.kernel

Class PolynomialKernel

java.lang.Object

elki.similarity.AbstractVectorSimilarity

elki.similarity.kernel.PolynomialKernel

All Implemented Interfaces:

Distance<NumberVector>, PrimitiveDistance<NumberVector>, PrimitiveSimilarity<NumberVector>, Similarity<NumberVector>

Direct Known Subclasses:

LinearKernel

public class PolynomialKernel
extends AbstractVectorSimilarity
implements PrimitiveDistance<NumberVector>

Polynomial Kernel function that computes a similarity between the two feature vectors x and y defined by \((x^T\cdot y+b)^{\text{degree}}\).

Since:

0.1

Author:

Simon Paradies

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	PolynomialKernel.Par	Parameterization class.

Field Summary

Fields

Modifier and Type	Field	Description
private double	bias	Bias of the similarity function.
static int	DEFAULT_DEGREE	The default degree.
private int	degree	Degree of the polynomial kernel function.

Constructor Summary

Constructors

Constructor	Description
PolynomialKernel(int degree)	Constructor.
PolynomialKernel(int degree, double bias)	Constructor.

Method Summary

Modifier and Type	Method	Description
double	distance(NumberVector fv1, NumberVector fv2)	Computes the distance between two given DatabaseObjects according to this distance function.
<T extends NumberVector> DistanceSimilarityQuery<T>	instantiate(Relation<T> database)	Instantiate with a database to get the actual distance query.
boolean	isMetric()	Is this distance function metric (satisfy the triangle inequality)
boolean	isSymmetric()	Is this function symmetric?
double	similarity(NumberVector o1, NumberVector o2)	Computes the similarity between two given DatabaseObjects according to this similarity function.

Methods inherited from class elki.similarity.AbstractVectorSimilarity

getInputTypeRestriction

Methods inherited from class java.lang.Object

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

Methods inherited from interface elki.distance.Distance

isSquared

Methods inherited from interface elki.distance.PrimitiveDistance

getInputTypeRestriction

Field Detail

DEFAULT_DEGREE

public static final int DEFAULT_DEGREE

The default degree.

See Also:

Constant Field Values

degree

private final int degree

Degree of the polynomial kernel function.

bias

private final double bias

Bias of the similarity function.

Constructor Detail

PolynomialKernel

public PolynomialKernel(int degree,
                        double bias)

Constructor.

Parameters:

degree - Kernel degree

bias - Bias offset

PolynomialKernel

public PolynomialKernel(int degree)

Constructor.

Parameters:

degree - Kernel degree

Method Detail

similarity

public double similarity(NumberVector o1,
                         NumberVector o2)

Description copied from interface: PrimitiveSimilarity

Computes the similarity between two given DatabaseObjects according to this similarity function.

Specified by:

similarity in interface PrimitiveSimilarity<NumberVector>

Parameters:

o1 - first DatabaseObject

o2 - second DatabaseObject

Returns:

the similarity between two given DatabaseObjects according to this similarity function

isSymmetric

public boolean isSymmetric()

Description copied from interface: Distance

Is this function symmetric?

Specified by:

isSymmetric in interface Distance<NumberVector>

Specified by:

isSymmetric in interface Similarity<NumberVector>

Returns:

true when symmetric

isMetric

public boolean isMetric()

Description copied from interface: Distance

Is this distance function metric (satisfy the triangle inequality)

Specified by:

isMetric in interface Distance<NumberVector>

Returns:

true when metric.

distance

public double distance(NumberVector fv1,
                       NumberVector fv2)

Description copied from interface: PrimitiveDistance

Computes the distance between two given DatabaseObjects according to this distance function.

Specified by:

distance in interface PrimitiveDistance<NumberVector>

Parameters:

fv1 - first DatabaseObject

fv2 - second DatabaseObject

Returns:

the distance between two given DatabaseObjects according to this distance function

instantiate

public <T extends NumberVector> DistanceSimilarityQuery<T> instantiate(Relation<T> database)

Description copied from interface: Distance

Instantiate with a database to get the actual distance query.

Specified by:

instantiate in interface Distance<NumberVector>

Specified by:

instantiate in interface PrimitiveDistance<NumberVector>

Specified by:

instantiate in interface PrimitiveSimilarity<NumberVector>

Specified by:

instantiate in interface Similarity<NumberVector>

Parameters:

database - The representation to use

Returns:

Actual distance query.