org.vizzini.ai.neuralnetwork
Class AbstractNeuralNetwork

java.lang.Object
  org.vizzini.ai.neuralnetwork.AbstractNeuralNetwork

All Implemented Interfaces:

Serializable, Cloneable, INeuralNetwork

Direct Known Subclasses:

DefaultNeuralNetwork, FeedForwardNetwork

abstract class AbstractNeuralNetwork
extends Object
implements INeuralNetwork

Provides base functionality for neural networks.

The network consists of an input layer, zero or more hidden layers, and an output layer. Layers before the output layer may optionally contain a bias node.

Since:

v0.1

Version:

v0.3

Author:

Jeffrey M. Thompson

Constructor Summary

AbstractNeuralNetwork()

Method Summary

void	addConnector(IConnector connector) Add the given connector.
void	addLayer(ILayer layer) Add the given layer.
void	adjustWeights(int fromLayer, int toLayer, double[][] deltas) Adjust the given layer's weights by adding the given deltas.
Object	clone() Return a clone of this instance.
void	configure(Properties properties) Configure this object using the given properties.
Iterator	connectorIterator(String toLayerName) Return an iterator over the collection of connectors with the given to layer.
boolean	equals(Object object) Return true if the given object is equal to this.
double[]	evaluate(double[] inputs) Apply the given inputs and return the output of the neural network.
void	fillWeights(double value) Assign the given value to all weights of the neural network.
IActivationFunction	getActivationFunction(int layerIndex) Return the activation function.
Properties	getConfiguration() Return the configuration of this network.
IConnector	getConnector(ILayer fromLayer, ILayer toLayer) Return the connector for the given parameters.
IConnector	getConnector(int fromLayerIndex, int toLayerIndex) Return the connector for the given parameters.
IConnector	getConnector(String fromLayerName, String toLayerName) Return the connector for the given parameters.
int	getConnectorCount() Return the number of connectors.
protected ConnectorCollection	getConnectors()
IScaler	getInputScaler() Return the input scaler.
ILayer	getLayer(int index) Return the layer at the given index.
int	getLayerCount() Return the number of layers.
protected List	getLayers()
int	getMaxOutputValueIndex() Return the index of the output node with the maximum value.
double	getNodeInput(int layerIndex, int i) Return the node input value for the given parameters.
double	getNodeOutput(int layerIndex, int i) Return the node output value for the given parameters.
ILayer	getOutputLayer() Return the output layer.
int	getOutputLayerIndex() Return the output layer index.
double[]	getOutputs() Return the output layer node values.
IScaler	getOutputScaler() Return the output scaler.
double	getWeight(int fromLayer, int i, int toLayer, int j) Return the weight for the given parameters.
double[]	getWeights(int fromLayer, int i, int toLayer) Return the weights for the given parameters.
int	hashCode() Returns a hash code value for the object.
int	indexOf(ILayer layer) Return the index of the given layer.
boolean	isConnected(ILayer fromLayer, ILayer toLayer) Return true if this network has a connector from the given layer to the given layer.
boolean	isConnected(int fromIndex, int toIndex) Return true if this network has a connector from the given layer to the given layer.
void	randomizeWeights() Assign random weights to the neural network in [-0.1,0.1].
void	randomizeWeights(double range) Assign random weights to the neural network.
void	setActivationFunction(IActivationFunction function) Set the activation function.
void	setActivationFunction(int layer, IActivationFunction function) Set the activation function for the given layer index.
protected void	setConnectors(ConnectorCollection connectors)
void	setInputs(double[] inputs) Set the values of the input nodes.
void	setInputScaler(IScaler scaler) Set the input scaler.
protected void	setLayers(List layers)
void	setNodeInput(int layerIndex, int i, double value) Set the node input value for the given parameters.
void	setOutputScaler(IScaler scaler) Set the output scaler.
void	setWeight(int fromLayer, int i, int toLayer, int j, double weight) Set the weight for the given parameters.
void	store(OutputStream outputStream) Store the neural network to the given output stream.
String	toString() Return a string representation of this object.
void	zeroWeights() Assign zero weights to the neural network.

Methods inherited from class java.lang.Object

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

Constructor Detail

AbstractNeuralNetwork

AbstractNeuralNetwork()

Method Detail

addConnector

public void addConnector(IConnector connector)

Add the given connector.

Specified by:

addConnector in interface INeuralNetwork

Parameters:

connector - Connector.

Since:

v0.3

addLayer

public void addLayer(ILayer layer)

Add the given layer.

Specified by:

addLayer in interface INeuralNetwork

Parameters:

layer - Layer.

Since:

v0.3

adjustWeights

public void adjustWeights(int fromLayer,
                          int toLayer,
                          double[][] deltas)

Adjust the given layer's weights by adding the given deltas.

Specified by:

adjustWeights in interface INeuralNetwork

Parameters:

fromLayer - From layer index, where 0=input layer, and layerCount-1=output layer.

toLayer - To layer index, where 0=input layer, and layerCount-1=output layer.

deltas - Weight deltas for the given layer.

Since:

v0.1

clone

public Object clone()

Return a clone of this instance.

Specified by:

clone in interface INeuralNetwork

Overrides:

clone in class Object

Since:

v0.1

configure

public void configure(Properties properties)
               throws InstantiationException,
                      IllegalAccessException

Configure this object using the given properties.

Specified by:

configure in interface INeuralNetwork

Throws:

InstantiationException

IllegalAccessException

Since:

v0.1

connectorIterator

public Iterator connectorIterator(String toLayerName)

Return an iterator over the collection of connectors with the given to layer.

Specified by:

connectorIterator in interface INeuralNetwork

Parameters:

toLayerName - To layer name.

Since:

v0.3

equals

public boolean equals(Object object)

Return true if the given object is equal to this.

Overrides:

equals in class Object

Parameters:

object - The object to compare.

Since:

v0.1

evaluate

public double[] evaluate(double[] inputs)

Apply the given inputs and return the output of the neural network.

Specified by:

evaluate in interface INeuralNetwork

Since:

v0.1

fillWeights

public void fillWeights(double value)

Assign the given value to all weights of the neural network.

Specified by:

fillWeights in interface INeuralNetwork

Since:

v0.3

getActivationFunction

public IActivationFunction getActivationFunction(int layerIndex)

Return the activation function.

Specified by:

getActivationFunction in interface INeuralNetwork

Parameters:

layerIndex - Layer index, where 0=input layer, and layerCount-1=output layer.

Since:

v0.1

getConfiguration

public Properties getConfiguration()

Return the configuration of this network. The input layer node count includes the bias node if used.

Specified by:

getConfiguration in interface INeuralNetwork

Since:

v0.1

getConnector

public IConnector getConnector(int fromLayerIndex,
                               int toLayerIndex)

Return the connector for the given parameters.

Specified by:

getConnector in interface INeuralNetwork

Parameters:

fromLayerIndex - From layer index.

toLayerIndex - To layer index.

Since:

v0.3

getConnector

public IConnector getConnector(ILayer fromLayer,
                               ILayer toLayer)

Return the connector for the given parameters.

Parameters:

fromLayer - From layer.

toLayer - To layer.

Since:

v0.3

getConnector

public IConnector getConnector(String fromLayerName,
                               String toLayerName)

Return the connector for the given parameters.

Parameters:

fromLayerName - From layer name.

toLayerName - To layer name.

Since:

v0.3

getConnectorCount

public int getConnectorCount()

Return the number of connectors.

Specified by:

getConnectorCount in interface INeuralNetwork

Since:

v0.3

getInputScaler

public IScaler getInputScaler()

Return the input scaler.

Specified by:

getInputScaler in interface INeuralNetwork

Since:

v0.1

getLayer

public ILayer getLayer(int index)

Return the layer at the given index.

Specified by:

getLayer in interface INeuralNetwork

Since:

v0.3

getLayerCount

public int getLayerCount()

Return the number of layers.

Specified by:

getLayerCount in interface INeuralNetwork

Since:

v0.1

getMaxOutputValueIndex

public int getMaxOutputValueIndex()

Return the index of the output node with the maximum value.

Specified by:

getMaxOutputValueIndex in interface INeuralNetwork

Since:

v0.1

getNodeInput

public double getNodeInput(int layerIndex,
                           int i)

Return the node input value for the given parameters.

Specified by:

getNodeInput in interface INeuralNetwork

Parameters:

layerIndex - Layer index, where 0=input layer, and layerCount-1=output layer.

i - Node index.

Since:

v0.3

getNodeOutput

public double getNodeOutput(int layerIndex,
                            int i)

Return the node output value for the given parameters.

Specified by:

getNodeOutput in interface INeuralNetwork

Parameters:

layerIndex - Layer index, where 0=input layer, and layerCount-1=output layer.

i - Node index.

Since:

v0.3

getOutputLayer

public ILayer getOutputLayer()

Return the output layer.

Specified by:

getOutputLayer in interface INeuralNetwork

Since:

v0.3

getOutputLayerIndex

public int getOutputLayerIndex()

Return the output layer index.

Specified by:

getOutputLayerIndex in interface INeuralNetwork

Since:

v0.3

getOutputs

public double[] getOutputs()

Return the output layer node values.

Specified by:

getOutputs in interface INeuralNetwork

Since:

v0.3

getOutputScaler

public IScaler getOutputScaler()

Return the output scaler.

Specified by:

getOutputScaler in interface INeuralNetwork

Since:

v0.1

getWeight

public double getWeight(int fromLayer,
                        int i,
                        int toLayer,
                        int j)

Return the weight for the given parameters.

Specified by:

getWeight in interface INeuralNetwork

Parameters:

fromLayer - From layer index, where 0=input layer, and layerCount-1=output layer.

i - From layer node index.

toLayer - To layer index, where 0=input layer, and layerCount-1=output layer.

j - To layer node index.

Since:

v0.1

getWeights

public double[] getWeights(int fromLayer,
                           int i,
                           int toLayer)

Return the weights for the given parameters.

Specified by:

getWeights in interface INeuralNetwork

Parameters:

fromLayer - From layer index, where 0=input layer, and layerCount-1=output layer.

i - From layer node index.

toLayer - To layer index, where 0=input layer, and layerCount-1=output layer.

Since:

v0.3

hashCode

public int hashCode()

Returns a hash code value for the object.

Overrides:

hashCode in class Object

Since:

v0.2

indexOf

public int indexOf(ILayer layer)

Return the index of the given layer.

Specified by:

indexOf in interface INeuralNetwork

Since:

v0.3

isConnected

public boolean isConnected(int fromIndex,
                           int toIndex)

Return true if this network has a connector from the given layer to the given layer.

Specified by:

isConnected in interface INeuralNetwork

Since:

v0.3

isConnected

public boolean isConnected(ILayer fromLayer,
                           ILayer toLayer)

Return true if this network has a connector from the given layer to the given layer.

Specified by:

isConnected in interface INeuralNetwork

Since:

v0.3

randomizeWeights

public void randomizeWeights()

Assign random weights to the neural network in [-0.1,0.1].

Specified by:

randomizeWeights in interface INeuralNetwork

Since:

v0.1

randomizeWeights

public void randomizeWeights(double range)

Assign random weights to the neural network.

Specified by:

randomizeWeights in interface INeuralNetwork

Parameters:

range - ±Range of random weights around zero.

Since:

v0.3

setActivationFunction

public void setActivationFunction(IActivationFunction function)

Set the activation function.

Specified by:

setActivationFunction in interface INeuralNetwork

Since:

v0.1

setActivationFunction

public void setActivationFunction(int layer,
                                  IActivationFunction function)

Set the activation function for the given layer index.

Specified by:

setActivationFunction in interface INeuralNetwork

Parameters:

layer - Layer index, where 0=input layer, and layerCount-1=output layer.

Since:

v0.3

setInputs

public void setInputs(double[] inputs)

Set the values of the input nodes.

Specified by:

setInputs in interface INeuralNetwork

Since:

v0.3

setInputScaler

public void setInputScaler(IScaler scaler)

Set the input scaler.

Specified by:

setInputScaler in interface INeuralNetwork

Since:

v0.1

setNodeInput

public void setNodeInput(int layerIndex,
                         int i,
                         double value)

Set the node input value for the given parameters.

Specified by:

setNodeInput in interface INeuralNetwork

Parameters:

layerIndex - Layer index, where 0=input layer, and layerCount-1=output layer.

i - Node index.

Since:

v0.3

setOutputScaler

public void setOutputScaler(IScaler scaler)

Set the output scaler.

Specified by:

setOutputScaler in interface INeuralNetwork

Since:

v0.1

setWeight

public void setWeight(int fromLayer,
                      int i,
                      int toLayer,
                      int j,
                      double weight)

Set the weight for the given parameters.

Specified by:

setWeight in interface INeuralNetwork

Parameters:

fromLayer - From layer index, where 0=input layer, and layerCount-1=output layer.

i - From layer node index.

toLayer - To layer index, where 0=input layer, and layerCount-1=output layer.

j - To layer node index.

weight - New weight.

Since:

v0.1

store

public void store(OutputStream outputStream)
           throws IOException

Store the neural network to the given output stream.

Specified by:

store in interface INeuralNetwork

Throws:

IOException

Since:

v0.1

toString

public String toString()

Return a string representation of this object.

Specified by:

toString in interface INeuralNetwork

Overrides:

toString in class Object

Since:

v0.1

zeroWeights

public void zeroWeights()

Assign zero weights to the neural network.

Specified by:

zeroWeights in interface INeuralNetwork

Since:

v0.3

getConnectors

protected ConnectorCollection getConnectors()

Returns:

Return connectors.

getLayers

protected List getLayers()

Returns:

Return layers.

setConnectors

protected void setConnectors(ConnectorCollection connectors)

Parameters:

connectors - the connectors to set

setLayers

protected void setLayers(List layers)

Parameters:

layers - the layers to set