org.encog.neural.networks.training.competitive.neighborhood
Interface NeighborhoodFunction

All Known Implementing Classes:

NeighborhoodBubble, NeighborhoodGaussian, NeighborhoodSingle

public interface NeighborhoodFunction

Defines how a neighborhood function should work in competitive training. This is most often used in the training process for a self-organizing map. This function determines to what degree the training should take place on a neuron, based on its proximity to the "winning" neuron.

Author:

jheaton

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.

Method Detail

function

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.

Parameters:

currentNeuron - THe current neuron being evaluated.

bestNeuron - The winning neuron.

Returns:

The ratio for this neuron's adjustment.