org.encog.neural.networks.layers
Class BasicLayer

java.lang.Object
  org.encog.neural.networks.layers.BasicLayer

All Implemented Interfaces:

Layer, EncogPersistedObject

Direct Known Subclasses:

FeedforwardLayer, HopfieldLayer, SOMLayer

public class BasicLayer
extends java.lang.Object
implements Layer, EncogPersistedObject

Basic functionality that most of the nueral layers require.

Author:

jheaton

Constructor Summary

BasicLayer(int neuronCount)
Construct a basic layer with the specified neuron count.

Method Summary

NeuralData	compute(NeuralData pattern) This layer is too basic to know how to compute a pattern, it simply passes the pattern on.
NeuralData	getFire() Get the output array from the last time that the output of this layer was calculated.
double	getFire(int index) Get the output from an individual neuron.
Matrix	getMatrix() Get the weight and threshold matrix.
int	getMatrixSize() Get the size of the matrix, or zero if one is not defined.
int	getNeuronCount() Get the neuron count for this layer.
Layer	getNext()
Layer	getPrevious()
boolean	hasMatrix() Determine if this layer has a matrix.
boolean	isHidden() Determine if this is a hidden layer.
boolean	isInput() Determine if this is an input layer.
boolean	isOutput() Determine if this is an output layer.
void	reset() Reset the weight matrix and threshold values to random numbers between -1 and 1.
void	setFire(int index, double f) Set the last output value for the specified neuron.
void	setFire(NeuralData fire) Set the fire data.
void	setMatrix(Matrix matrix) Assign a new weight and threshold matrix to this layer.
void	setNext(Layer next) Set the next layer.
void	setPrevious(Layer previous) Set the previous layer.

Methods inherited from class java.lang.Object

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

Constructor Detail

BasicLayer

public BasicLayer(int neuronCount)

Construct a basic layer with the specified neuron count.

Parameters:

neuronCount - How many neurons does this layer have.

Method Detail

compute

public NeuralData compute(NeuralData pattern)

This layer is too basic to know how to compute a pattern, it simply passes the pattern on.

Specified by:

compute in interface Layer

Parameters:

pattern - The pattern to compute against.

Returns:

The input pattern is returned.

getFire

public NeuralData getFire()

Get the output array from the last time that the output of this layer was calculated.

Specified by:

getFire in interface Layer

Returns:

The output array.

getFire

public double getFire(int index)

Get the output from an individual neuron.

Parameters:

index - The neuron specified.

Returns:

The output from the specified neuron.

getMatrix

public Matrix getMatrix()

Get the weight and threshold matrix.

Specified by:

getMatrix in interface Layer

Returns:

The weight and threshold matrix.

getMatrixSize

public int getMatrixSize()

Get the size of the matrix, or zero if one is not defined.

Specified by:

getMatrixSize in interface Layer

Returns:

The size of the matrix.

getNeuronCount

public int getNeuronCount()

Get the neuron count for this layer.

Specified by:

getNeuronCount in interface Layer

Returns:

the neuronCount

getNext

public Layer getNext()

Specified by:

getNext in interface Layer

Returns:

the next layer.

getPrevious

public Layer getPrevious()

Returns:

the previous layer.

hasMatrix

public boolean hasMatrix()

Determine if this layer has a matrix.

Specified by:

hasMatrix in interface Layer

Returns:

True if this layer has a matrix.

isHidden

public boolean isHidden()

Determine if this is a hidden layer.

Specified by:

isHidden in interface Layer

Returns:

True if this is a hidden layer.

isInput

public boolean isInput()

Determine if this is an input layer.

Specified by:

isInput in interface Layer

Returns:

True if this is an input layer.

isOutput

public boolean isOutput()

Determine if this is an output layer.

Specified by:

isOutput in interface Layer

Returns:

True if this is an output layer.

reset

public void reset()

Reset the weight matrix and threshold values to random numbers between -1 and 1.

Specified by:

reset in interface Layer

setFire

public void setFire(int index,
                    double f)

Set the last output value for the specified neuron.

Specified by:

setFire in interface Layer

Parameters:

index - The specified neuron.

f - The fire value for the specified neuron.

setFire

public void setFire(NeuralData fire)

Set the fire data.

Specified by:

setFire in interface Layer

Parameters:

fire - The fire data.

setMatrix

public void setMatrix(Matrix matrix)

Assign a new weight and threshold matrix to this layer.

Specified by:

setMatrix in interface Layer

Parameters:

matrix - The new matrix.

setNext

public void setNext(Layer next)

Set the next layer.

Specified by:

setNext in interface Layer

Parameters:

next - the next layer.

setPrevious

public void setPrevious(Layer previous)

Set the previous layer.

Specified by:

setPrevious in interface Layer

Parameters:

previous - the previous layer.