de.htwdd.rosenkoenig.neuro.net
Class InputLayer

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

Direct Known Subclasses:

KohonenLayer

public class InputLayer
extends Layer

This class represents an input layer.

Field Summary

protected double[]	input The array containing the input of the InputLayer.
private int	inputSize The input size of this layer (i.e. the number of inputs per pattern).

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

activationFunction, biased, nettoInput, neuronsThatAreNotBiasedCount, output, outputSynapse

Constructor Summary

InputLayer()
Default ctor.

InputLayer(int numNeurons, boolean biased)
Ctor that creates an InputLayer with numNeurons that is biased or not.

InputLayer(int numNeurons, boolean biased, ActivationFunction activationFunction)
Ctor that creates a InnerLayer with numNeurons that is biased or not.

Method Summary

double[]	getInput() Getter of the property input
void	propagate() Propagate a pattern through the net.
void	setInput(double[] input) Setter of the property input

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

inputSize

private int inputSize

The input size of this layer (i.e. the number of inputs per pattern). This value is an equivalent to the number of neurons in an input layer.

input

protected double[] input

The array containing the input of the InputLayer.

Constructor Detail

InputLayer

public InputLayer()

Default ctor.

InputLayer

public InputLayer(int numNeurons,
                  boolean biased)

Ctor that creates an InputLayer with numNeurons that is biased or not. The activation function remains the identity function.

Parameters:

numNeurons - the number of neurons for this InputLayer

biased - whether or not this InputLayer is a biased one

InputLayer

public InputLayer(int numNeurons,
                  boolean biased,
                  ActivationFunction activationFunction)

Ctor that creates a InnerLayer with numNeurons that is biased or not. The activation function remains will be set to the activation function you specify.

Parameters:

numNeurons - the number of neurons for this InputLayer

biased - whether or not this InputLayer is a biased one

Method Detail

getInput

public double[] getInput()

Getter of the property input

Returns:

Returns the inputs.

setInput

public void setInput(double[] input)

Setter of the property input

Parameters:

input - The inputs to set.

propagate

public void propagate()

Propagate a pattern through the net. For an InputLayer this only means that the input becomes the nettoInput.

Specified by:

propagate in class Layer