org.encog.neural.networks.training.competitive.neighborhood
Class NeighborhoodGaussian

java.lang.Object
  org.encog.neural.networks.training.competitive.neighborhood.NeighborhoodGaussian

All Implemented Interfaces:

NeighborhoodFunction

public class NeighborhoodGaussian
extends java.lang.Object
implements NeighborhoodFunction

A neighborhood function based on the Gaussian function.

Author:

jheaton

Constructor Summary

NeighborhoodGaussian(RadialBasisFunction radial)
Construct the neighborhood function with the specified radial function.

Method Summary

double

function(int currentNeuron, int bestNeuron) Determine how much the current neuron should be affected by training based on its proximity to the winning neuron.

Methods inherited from class java.lang.Object

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

Constructor Detail

NeighborhoodGaussian

public NeighborhoodGaussian(RadialBasisFunction radial)

Construct the neighborhood function with the specified radial function. Generally this will be a Gaussian function but any RBF should do.

Parameters:

radial - The radial basis function to use.

Method Detail

function

public double function(int currentNeuron,
                       int bestNeuron)

Determine how much the current neuron should be affected by training based on its proximity to the winning neuron.

Specified by:

function in interface NeighborhoodFunction

Parameters:

currentNeuron - THe current neuron being evaluated.

bestNeuron - The winning neuron.

Returns:

The ratio for this neuron's adjustment.