org.joone.engine

Interface NeuralLayer

All Known Subinterfaces:

LearnableLayer

All Known Implementing Classes:

BiasedLinearLayer, ContextLayer, DelayLayer, GaussianLayer, GaussLayer, Layer, LinearLayer, LogarithmicLayer, MemoryLayer, NestedNeuralLayer, NeuralNet, RbfGaussianLayer, RbfLayer, SigmoidLayer, SimpleLayer, SineLayer, SoftmaxLayer, TanhLayer, WTALayer

public interface NeuralLayer

This is the interface for all the layer objects of the neural network

Method Summary

Modifier and Type	Method and Description
boolean	addInputSynapse(InputPatternListener newListener) Adds a new input synapse to the layer
void	addNoise(double amplitude) Adds a noise to the biases of the layer and to all the input synapses connected
boolean	addOutputSynapse(OutputPatternListener newListener) Adds a new output synapse to the layer
java.util.TreeSet	check() Validation checks for invalid parameter values, misconfiguration, etc.
NeuralLayer	copyInto(NeuralLayer newLayer) Copies a Layer into another one, to obtain a type-transformation from a kind of Layer to another.
java.util.Vector	getAllInputs() Returns the vector of the input listeners
java.util.Vector	getAllOutputs() Returns the vector of the input listeners
Matrix	getBias() Return the bias matrix
java.lang.String	getLayerName() Returns the name of the layer
Monitor	getMonitor() Returns the monitor object
int	getRows() Returns the dimension (# of neurons) of the Layer
boolean	isRunning() Returns true if the layer is running
void	removeAllInputs() Remove all the input listeners of the net
void	removeAllOutputs() Remove all the output listeners of the net
void	removeInputSynapse(InputPatternListener newListener) Remove an input Listener
void	removeOutputSynapse(OutputPatternListener newListener) Remove an output listener from the layer
void	setAllInputs(java.util.Vector newAInputPatternListener) Sets the vector that contains all the input listeners.
void	setAllOutputs(java.util.Vector newAOutputPatternListener) Sets the vector that contains all the output listeners.
void	setBias(Matrix newBias) Sets the matrix of biases
void	setLayerName(java.lang.String newLayerName) Sets the name of the layer
void	setMonitor(Monitor newMonitor) Sets the monitor object
void	setRows(int newRows) Sets the dimension (# of neurons) of the Layer
void	start() Starts the Layer

Method Detail

addNoise

void addNoise(double amplitude)

Adds a noise to the biases of the layer and to all the input synapses connected

Parameters:

amplitude - the noise's amplitude in terms of distance from zero; e.g.: a value equal 0.3 means a noise from -0.3 to 0.3

copyInto

NeuralLayer copyInto(NeuralLayer newLayer)

Copies a Layer into another one, to obtain a type-transformation from a kind of Layer to another. The old Layer is disconnected from the net, while the new Layer takes its place.

Parameters:

newLayer - neural.engine.Layer

Returns:

The new layer

getAllInputs

java.util.Vector getAllInputs()

Returns the vector of the input listeners

Returns:

java.util.Vector

getAllOutputs

java.util.Vector getAllOutputs()

Returns the vector of the input listeners

Returns:

java.util.Vector

getBias

Matrix getBias()

Return the bias matrix

Returns:

neural.engine.Matrix

getLayerName

java.lang.String getLayerName()

Returns the name of the layer

Returns:

java.lang.String

getRows

int getRows()

Returns the dimension (# of neurons) of the Layer

Returns:

int

removeAllInputs

void removeAllInputs()

Remove all the input listeners of the net

removeAllOutputs

void removeAllOutputs()

Remove all the output listeners of the net

removeInputSynapse

void removeInputSynapse(InputPatternListener newListener)

Remove an input Listener

Parameters:

newListener - the input listener to remove

removeOutputSynapse

void removeOutputSynapse(OutputPatternListener newListener)

Remove an output listener from the layer

Parameters:

newListener - the output listener to remove

setAllInputs

void setAllInputs(java.util.Vector newAInputPatternListener)

Sets the vector that contains all the input listeners. Can be useful to set the input synapses taken from another Layer

Parameters:

newAInputPatternListener - The vector containing the list of input synapses

setAllOutputs

void setAllOutputs(java.util.Vector newAOutputPatternListener)

Sets the vector that contains all the output listeners. Can be useful to set the output synapses taken from another Layer

Parameters:

newAOutputPatternListener - The vector containing the list of output synapses

setBias

void setBias(Matrix newBias)

Sets the matrix of biases

Parameters:

newBias - The Matrix object containing the biases

addInputSynapse

boolean addInputSynapse(InputPatternListener newListener)

Adds a new input synapse to the layer

Parameters:

newListener - The new input synapse

Returns:

true if the input synapse has been attached sucessfully

setLayerName

void setLayerName(java.lang.String newLayerName)

Sets the name of the layer

Parameters:

newLayerName - The name

addOutputSynapse

boolean addOutputSynapse(OutputPatternListener newListener)

Adds a new output synapse to the layer

Parameters:

newListener - The new output synapse

Returns:

true if the output synapse has been attached sucessfully

setRows

void setRows(int newRows)

Sets the dimension (# of neurons) of the Layer

Parameters:

newRows - The number of the neurons contained in the Layer

start

void start()

Starts the Layer

setMonitor

void setMonitor(Monitor newMonitor)

Sets the monitor object

Parameters:

newMonitor - The Monitor to be set

getMonitor

Monitor getMonitor()

Returns the monitor object

Returns:

java.engine.Monitor

isRunning

boolean isRunning()

Returns true if the layer is running

Returns:

boolean

check

java.util.TreeSet check()

Validation checks for invalid parameter values, misconfiguration, etc. All network components should include a check method that firstly calls its ancestor check method and adds these to any check messages it produces. This allows check messages to be collected from all levels of a component to be returned to the caller's check method. Using a TreeSet ensures that duplicate messages are removed. Check messages should be produced using the generateValidationErrorMessage method of the NetChecker class.

Returns:

validation errors.