org.encog.neural.networks
Class BasicNetwork

java.lang.Object
  org.encog.neural.networks.BasicNetwork

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, Network, EncogPersistedObject

public class BasicNetwork
extends java.lang.Object
implements java.io.Serializable, Network

This class implements a neural network. This class works in conjunction the Layer classes. Layers are added to the BasicNetwork to specify the structure of the neural network. The first layer added is the input layer, the final layer added is the output layer. Any layers added between these two layers are the hidden layers. The network structure is stored in the structure member. It is important to call: network.getStructure().finalizeStructure(); Once the neural network has been completely constructed.

See Also:

Serialized Form

Constructor Summary

BasicNetwork()
Construct an empty neural network.

Method Summary

void	addLayer(Layer layer) Add a layer to the neural network.
void	addLayer(Layer layer, SynapseType type) Add a layer to the neural network.
double	calculateError(NeuralDataSet data) Calculate the error for this neural network.
int	calculateNeuronCount() Calculate the total number of neurons in the network across all layers.
void	checkInputSize(NeuralData input) Check that the input size is acceptable, if it does not match the input layer, then throw an error.
java.lang.Object	clone() Return a clone of this neural network.
boolean	compareLayer(Layer layerThis, Layer layerOther, int precision) Used to compare one neural network to another, compare two layers.
NeuralData	compute(NeuralData input) Compute the output for a given input to the neural network.
NeuralData	compute(NeuralData input, NeuralOutputHolder useHolder) Compute the output for a given input to the neural network.
Persistor	createPersistor() Create a persistor for this object.
boolean	equals(BasicNetwork other) Compare the two neural networks.
boolean	equals(BasicNetwork other, int precision) Determine if this neural network is equal to another.
java.lang.String	getDescription()
int	getHiddenLayerCount() Get the count for how many hidden layers are present.
java.util.Collection<Layer>	getHiddenLayers() Get a collection of the hidden layers in the network.
Layer	getInputLayer() Get the input layer.
java.lang.String	getName()
Layer	getOutputLayer() Get the output layer.
NeuralStructure	getStructure()
int	getWeightMatrixSize()
int	hashCode() Generate a hash code.
void	inferOutputLayer() Called to cause the network to attempt to infer which layer should be the output layer.
boolean	isHidden(Layer layer) Determine if this layer is hidden.
boolean	isInput(Layer layer) Determine if this layer is the input layer.
boolean	isOutput(Layer layer) Determine if this layer is the output layer.
void	reset() Reset the weight matrix and the thresholds.
void	setDescription(java.lang.String theDescription) Set the description for this object.
void	setInputLayer(Layer input) Define the input layer for the network.
void	setName(java.lang.String name) Set the name of this object.
void	setOutputLayer(Layer outputLayer)
java.lang.String	toString()
int	winner(NeuralData input) Determine the winner for the specified input.

Methods inherited from class java.lang.Object

equals, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

BasicNetwork

public BasicNetwork()

Construct an empty neural network.

Method Detail

addLayer

public void addLayer(Layer layer)

Add a layer to the neural network. The first layer added is the input layer, the last layer added is the output layer. This layer is added with a weighted synapse.

Specified by:

addLayer in interface Network

Parameters:

layer - The layer to be added.

addLayer

public void addLayer(Layer layer,
                     SynapseType type)

Add a layer to the neural network. If there are no layers added this layer will become the input layer. This function automatically updates both the input and output layer references.

Specified by:

addLayer in interface Network

Parameters:

layer - The layer to be added to the network.

type - What sort of synapse should connect this layer to the last.

calculateError

public double calculateError(NeuralDataSet data)

Calculate the error for this neural network. The error is calculated using root-mean-square(RMS).

Specified by:

calculateError in interface Network

Parameters:

data - The training set.

Returns:

The error percentage.

calculateNeuronCount

public int calculateNeuronCount()

Calculate the total number of neurons in the network across all layers.

Specified by:

calculateNeuronCount in interface Network

Returns:

The neuron count.

checkInputSize

public void checkInputSize(NeuralData input)

Check that the input size is acceptable, if it does not match the input layer, then throw an error.

Specified by:

checkInputSize in interface Network

Parameters:

input - The input data.

clone

public java.lang.Object clone()

Return a clone of this neural network. Including structure, weights and threshold values.

Specified by:

clone in interface Network

Specified by:

clone in interface EncogPersistedObject

Overrides:

clone in class java.lang.Object

Returns:

A cloned copy of the neural network.

compareLayer

public boolean compareLayer(Layer layerThis,
                            Layer layerOther,
                            int precision)

Used to compare one neural network to another, compare two layers.

Specified by:

compareLayer in interface Network

Parameters:

layerThis - The layer being compared.

layerOther - The other layer.

precision - The precision to use, how many decimal places.

Returns:

Returns true if the two layers are the same.

compute

public NeuralData compute(NeuralData input)

Compute the output for a given input to the neural network.

Specified by:

compute in interface Network

Parameters:

input - The input to the neural network.

Returns:

The output from the neural network.

compute

public NeuralData compute(NeuralData input,
                          NeuralOutputHolder useHolder)

Compute the output for a given input to the neural network. This method provides a parameter to specify an output holder to use. This holder allows propagation training to track the output from each layer. If you do not need this holder pass null, or use the other compare method.

Specified by:

compute in interface Network

Parameters:

input - The input provide to the neural network.

useHolder - Allows a holder to be specified, this allows propagation training to check the output of each layer.

Returns:

The results from the output neurons.

createPersistor

public Persistor createPersistor()

Create a persistor for this object.

Specified by:

createPersistor in interface Network

Specified by:

createPersistor in interface EncogPersistedObject

Returns:

The newly created persistor.

equals

public boolean equals(BasicNetwork other)

Compare the two neural networks. For them to be equal they must be of the same structure, and have the same matrix values.

Specified by:

equals in interface Network

Parameters:

other - The other neural network.

Returns:

True if the two networks are equal.

equals

public boolean equals(BasicNetwork other,
                      int precision)

Determine if this neural network is equal to another. Equal neural networks have the same weight matrix and threshold values, within a specified precision.

Specified by:

equals in interface Network

Parameters:

other - The other neural network.

precision - The number of decimal places to compare to.

Returns:

True if the two neural networks are equal.

getDescription

public java.lang.String getDescription()

Specified by:

getDescription in interface Network

Specified by:

getDescription in interface EncogPersistedObject

Returns:

The description for this object.

getHiddenLayerCount

public int getHiddenLayerCount()

Get the count for how many hidden layers are present.

Specified by:

getHiddenLayerCount in interface Network

Returns:

The hidden layer count.

getHiddenLayers

public java.util.Collection<Layer> getHiddenLayers()

Get a collection of the hidden layers in the network.

Specified by:

getHiddenLayers in interface Network

Returns:

The hidden layers.

getInputLayer

public Layer getInputLayer()

Get the input layer.

Specified by:

getInputLayer in interface Network

Returns:

The input layer.

getName

public java.lang.String getName()

Specified by:

getName in interface Network

Specified by:

getName in interface EncogPersistedObject

Returns:

the name

getOutputLayer

public Layer getOutputLayer()

Get the output layer.

Specified by:

getOutputLayer in interface Network

Returns:

The output layer.

getStructure

public NeuralStructure getStructure()

Specified by:

getStructure in interface Network

Returns:

Get the structure of the neural network. The structure allows you to quickly obtain synapses and layers without traversing the network.

getWeightMatrixSize

public int getWeightMatrixSize()

Specified by:

getWeightMatrixSize in interface Network

Returns:

The size of the matrix.

hashCode

public int hashCode()

Generate a hash code.

Specified by:

hashCode in interface Network

Overrides:

hashCode in class java.lang.Object

Returns:

THe hash code.

inferOutputLayer

public void inferOutputLayer()

Called to cause the network to attempt to infer which layer should be the output layer.

Specified by:

inferOutputLayer in interface Network

isHidden

public boolean isHidden(Layer layer)

Determine if this layer is hidden.

Specified by:

isHidden in interface Network

Parameters:

layer - The layer to evaluate.

Returns:

True if this layer is a hidden layer.

isInput

public boolean isInput(Layer layer)

Determine if this layer is the input layer.

Specified by:

isInput in interface Network

Parameters:

layer - The layer to evaluate.

Returns:

True if this layer is the input layer.

isOutput

public boolean isOutput(Layer layer)

Determine if this layer is the output layer.

Specified by:

isOutput in interface Network

Parameters:

layer - The layer to evaluate.

Returns:

True if this layer is the output layer.

reset

public void reset()

Reset the weight matrix and the thresholds.

Specified by:

reset in interface Network

setDescription

public void setDescription(java.lang.String theDescription)

Set the description for this object.

Specified by:

setDescription in interface Network

Specified by:

setDescription in interface EncogPersistedObject

Parameters:

theDescription - The description.

setInputLayer

public void setInputLayer(Layer input)

Define the input layer for the network.

Specified by:

setInputLayer in interface Network

Parameters:

input - The new input layer.

setName

public void setName(java.lang.String name)

Description copied from interface: EncogPersistedObject

Set the name of this object.

Specified by:

setName in interface Network

Specified by:

setName in interface EncogPersistedObject

Parameters:

name - the name to set

setOutputLayer

public void setOutputLayer(Layer outputLayer)

Specified by:

setOutputLayer in interface Network

Parameters:

outputLayer - the outputLayer to set

toString

public java.lang.String toString()

Specified by:

toString in interface Network

Overrides:

toString in class java.lang.Object

Returns:

Convert this object to a string.

winner

public int winner(NeuralData input)

Determine the winner for the specified input. This is the number of the winning neuron.

Specified by:

winner in interface Network

Parameters:

input - The input patter to present to the neural network.

Returns:

The winning neuron.