de.htwdd.rosenkoenig.neuro.net
Class WinnerTakesAll

java.lang.Object
  de.htwdd.rosenkoenig.neuro.net.NeighbourhoodFunction
      de.htwdd.rosenkoenig.neuro.net.WinnerTakesAll

public class WinnerTakesAll
extends NeighbourhoodFunction

The WinnerTakesAll neighbourhood function gives the same activation (1.0) to all neurons within the neighbourhood radius.

Field Summary

Fields inherited from class de.htwdd.rosenkoenig.neuro.net.NeighbourhoodFunction

radius

Constructor Summary

WinnerTakesAll()
Default constructor.

Method Summary

double

computeActivation(double distance) All neighbourhood functions have to implement this method.

Methods inherited from class de.htwdd.rosenkoenig.neuro.net.NeighbourhoodFunction

getRadius, setRadius

Methods inherited from class java.lang.Object

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

Constructor Detail

WinnerTakesAll

public WinnerTakesAll()

Default constructor.

Method Detail

computeActivation

public double computeActivation(double distance)

Description copied from class: NeighbourhoodFunction

All neighbourhood functions have to implement this method. Computes the activation of a neuran with a certain distance to the winning neuron.

Specified by:

computeActivation in class NeighbourhoodFunction

Parameters:

distance - euclidic distance to the winning neuron

Returns:

1.0 if distance <= radius, 0.0 else