de.htwdd.rosenkoenig.neuro.net
Class KohonenLayer

java.lang.Object
  de.htwdd.rosenkoenig.neuro.net.Layer
      de.htwdd.rosenkoenig.neuro.net.InputLayer
          de.htwdd.rosenkoenig.neuro.net.KohonenLayer

public class KohonenLayer
extends InputLayer

This wrapper class is needed to use a KohonenNet as input layer for a FeedForwardNet.

Field Summary

private KohonenNet

kohonenNet The Kohonen map wrapped by this KohonenLayer.

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

input

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

activationFunction, biased, nettoInput, neuronsThatAreNotBiasedCount, output, outputSynapse

Constructor Summary

KohonenLayer()
Default constructor, needed to extract a Kohonen layer from XML.

KohonenLayer(KohonenNet kohonenNet, boolean biased)
Creates and initializes a new KohonenLayer.

Method Summary

KohonenNet	getKohonenNet() Getter of the property kohonenNet
void	propagate() Determines this layer's output by propagating the input to the wrapped KohonenNet.
void	setInput(double[] input) Setter of the property input
void	setKohonenNet(KohonenNet kohonenNet) Setter of the property kohonenNet

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

getInput

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

getActivationFunction, getNettoInput, getNeuronsThatAreNotBiasedCount, getOutput, getOutputSynapse, getSize, isBiased, setActivationFunction, setBiased, setOutputSynapse

Methods inherited from class java.lang.Object

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

Field Detail

kohonenNet

private KohonenNet kohonenNet

The Kohonen map wrapped by this KohonenLayer.

Constructor Detail

KohonenLayer

public KohonenLayer()

Default constructor, needed to extract a Kohonen layer from XML.

KohonenLayer

public KohonenLayer(KohonenNet kohonenNet,
                    boolean biased)

Creates and initializes a new KohonenLayer.

Parameters:

kohonenNet - the Kohonen map wrapped by this KohonenLayer

biased - if true, the input layer will be biased

Method Detail

getKohonenNet

public KohonenNet getKohonenNet()

Getter of the property kohonenNet

Returns:

Returns the kohonenNet.

setKohonenNet

public void setKohonenNet(KohonenNet kohonenNet)

Setter of the property kohonenNet

Parameters:

kohonenNet - The kohonenNet to set.

setInput

public void setInput(double[] input)

Setter of the property input

Overrides:

setInput in class InputLayer

Parameters:

input - The inputs to set.

propagate

public void propagate()

Determines this layer's output by propagating the input to the wrapped KohonenNet.

Overrides:

propagate in class InputLayer