NearNeural

Class NeuronLayer

java.lang.Object

NearNeural.NeuronLayer

Direct Known Subclasses:

ReceptiveNeuronLayer, StaticNeuronLayer

public abstract class NeuronLayer
extends java.lang.Object

A NeuronLayer keeps track of an arbitrary selection of neurons, each of which may have arbitrary or even circular links. It is not possible to run the back propogation algorithms without restricting this class' contents and fixing the structure of the net. This class's subclasses enable this. There is no reason why this class should not be used, but for executing nets it is useless.

Version:

0.2.0a

Author:

Stephen Wattam

Field Summary

Fields

Modifier and Type	Field and Description
protected Neuron[]	neurons Stores all Neurons in this layer
protected ThresholdingAlgorithm	thresholdModel The thresholding model to use for back propagation

Constructor Summary

Constructors

Constructor and Description
NeuronLayer(ThresholdingAlgorithm p_thresholdModel) Creates a blank neuron layer with the threshold model provided.

Method Summary

Methods

Modifier and Type	Method and Description
void	addNeuron(Neuron p_neuron) Adds a neuron to the layer.
int	countNeurons() Returns the number of neurons currently in this layer.
Neuron	getNeuron(int p_index) Returns a neuron with the index provided
Neuron[]	getNeurons() Returns all Neurons in this layer.
boolean	isPresent(Neuron p_neuron) checks if a Neuron is held in this layer.
void	removeNeuron(int p_index) Removes a neuron from the layer by index.
void	removeNeuron(Neuron p_neuron) Removes a neuron from this layer.

Methods inherited from class java.lang.Object

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

Field Detail

thresholdModel

protected ThresholdingAlgorithm thresholdModel

The thresholding model to use for back propagation

neurons

protected Neuron[] neurons

Stores all Neurons in this layer

See Also:

Neuron

Constructor Detail

NeuronLayer

public NeuronLayer(ThresholdingAlgorithm p_thresholdModel)

Creates a blank neuron layer with the threshold model provided.

Parameters:

p_thresholdModel - The thresholding algorithm chosen

Method Detail

addNeuron

public void addNeuron(Neuron p_neuron)

Adds a neuron to the layer.

Parameters:

p_neuron - The neuron to add to this layer.

removeNeuron

public void removeNeuron(Neuron p_neuron)
                  throws ItemNotFoundException

Removes a neuron from this layer.

Parameters:

p_neuron - The neuron to remove.

Throws:

ItemNotFoundException - if the neuron passed is not present.

removeNeuron

public void removeNeuron(int p_index)
                  throws IndexOutOfBoundsException

Removes a neuron from the layer by index.

Parameters:

p_index - The index of the neuron to remove

Throws:

IndexOutOfBoundsException - in the event that the index given is out of range.

countNeurons

public int countNeurons()

Returns the number of neurons currently in this layer.

Returns:

The number of neurons currently in the layer

getNeuron

public Neuron getNeuron(int p_index)
                 throws IndexOutOfBoundsException

Returns a neuron with the index provided

Parameters:

p_index - The index of the Neuron to return

Returns:

The neuron at the index specified

Throws:

IndexOutOfBoundsException - in the event that the index is out of range.

getNeurons

public Neuron[] getNeurons()

Returns all Neurons in this layer. This is used largely to ensure that the load and save routines can inject values directly from the tokenised file stream.

Returns:

An array of all Neurons held

isPresent

public boolean isPresent(Neuron p_neuron)

checks if a Neuron is held in this layer.

Parameters:

p_neuron - The neuron to check for

Returns:

true if the neuron is present, false if it is not