gov.sandia.cognition.learning.function.kernel
Class KernelDistanceMetric<InputType>

java.lang.Object
  extended by gov.sandia.cognition.util.AbstractCloneableSerializable
      extended by gov.sandia.cognition.learning.function.kernel.DefaultKernelContainer<InputType>
          extended by gov.sandia.cognition.learning.function.kernel.KernelDistanceMetric<InputType>
Type Parameters:
InputType - The type of the input to the Kernel. For example, Vector.
All Implemented Interfaces:
KernelContainer<InputType>, DivergenceFunction<InputType,InputType>, Metric<InputType>, Semimetric<InputType>, CloneableSerializable, Serializable, Cloneable

@CodeReview(reviewer="Kevin R. Dixon",
            date="2009-07-08",
            changesNeeded=false,
            comments={"Made clone call super.clone.","Looks fine otherwise."})
public class KernelDistanceMetric<InputType>
extends DefaultKernelContainer<InputType>
implements Metric<InputType>

The KernelDistanceMetric class implements a distance metric that utilizes an underlying Kernel for computing the distance. The distance is computed as:
d(x, y) = k(x, x) + k(y, y) - 2 * k(x, y)

Since:
2.0
Author:
Justin Basilico
See Also:
Serialized Form

Field Summary
 
Fields inherited from class gov.sandia.cognition.learning.function.kernel.DefaultKernelContainer
kernel
 
Constructor Summary
KernelDistanceMetric()
          Creates a new instance of KernelDistanceMetric.
KernelDistanceMetric(Kernel<? super InputType> kernel)
          Creates a new instance of KernelDistanceMetric using the given kernel.
KernelDistanceMetric(KernelDistanceMetric<InputType> other)
          Creates a new copy of a KernelDistanceMetric.
 
Method Summary
 KernelDistanceMetric<InputType> clone()
          This makes public the clone method on the Object class and removes the exception that it throws.
 double evaluate(InputType first, InputType second)
          Computes the distance between the two given objects using the Kernel it was given.
 
Methods inherited from class gov.sandia.cognition.learning.function.kernel.DefaultKernelContainer
getKernel, setKernel
 
Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

KernelDistanceMetric

public KernelDistanceMetric()
Creates a new instance of KernelDistanceMetric. The kernel is initialized to null.


KernelDistanceMetric

public KernelDistanceMetric(Kernel<? super InputType> kernel)
Creates a new instance of KernelDistanceMetric using the given kernel.

Parameters:
kernel - The kernel to use.

KernelDistanceMetric

public KernelDistanceMetric(KernelDistanceMetric<InputType> other)
Creates a new copy of a KernelDistanceMetric.

Parameters:
other - The KernelDistanceMetric to copy.
Method Detail

clone

public KernelDistanceMetric<InputType> clone()
Description copied from class: AbstractCloneableSerializable
This makes public the clone method on the Object class and removes the exception that it throws. Its default behavior is to automatically create a clone of the exact type of object that the clone is called on and to copy all primitives but to keep all references, which means it is a shallow copy. Extensions of this class may want to override this method (but call super.clone() to implement a "smart copy". That is, to target the most common use case for creating a copy of the object. Because of the default behavior being a shallow copy, extending classes only need to handle fields that need to have a deeper copy (or those that need to be reset). Some of the methods in ObjectUtil may be helpful in implementing a custom clone method. Note: The contract of this method is that you must use super.clone() as the basis for your implementation.

Specified by:
clone in interface CloneableSerializable
Overrides:
clone in class DefaultKernelContainer<InputType>
Returns:
A clone of this object.

evaluate

public double evaluate(InputType first,
                       InputType second)
Computes the distance between the two given objects using the Kernel it was given. The distance is computed as:
d(x, y) = k(x, x) + k(y, y) - 2 * k(x, y)

Specified by:
evaluate in interface DivergenceFunction<InputType,InputType>
Parameters:
first - The first value.
second - The second value.
Returns:
The distance between the two given objects as computed using the kernel.