Overview  Package   Class  Use  Deprecated  Index
Home >> All >> org >> joone >> [ engine overview ]	PREV CLASS  NEXT CLASS
SUMMARY:  JAVADOC |  SOURCE |  DOWNLOAD | NESTED | FIELD | CONSTR | METHOD	DETAIL: FIELD | CONSTR | METHOD

---

org.joone.engine
Class Layer  

java.lang.Object
  org.joone.engine.Layer

All Implemented Interfaces:

java.util.EventListener, org.joone.inspection.Inspectable, Learnable, LearnableLayer, NeuralLayer, NeuralNetListener, java.lang.Runnable, java.io.Serializable

Direct Known Subclasses:

MemoryLayer, RbfLayer, SimpleLayer

---

public abstract class Layer

extends java.lang.Object

implements NeuralLayer, java.lang.Runnable, java.io.Serializable, org.joone.inspection.Inspectable, LearnableLayer, NeuralNetListener

The Layer object is the basic element forming the neural net. Primarily it consists of a number of neurons that apply a transfer function to the sum of a number of input patterns and convey the result to the output pattern. The input patterns are received from connected input listeners and the transformed results are passed to connected output listeners. The component also handles learning by accepting patterns of error gradients from output listeners, applying a reverse (inverse) transfer function and passing the result to the input listeners. Layers execute their own Threads to perform the perform the pattern conveyance, so that a network of Layers can operate in a multi-threaded manner. The execution and termination of the Thread is controlled by a Monitor object.

---

Field Summary
protected  Matrix	bias           Holds the bias of neurons of the layer
protected  double[]	gradientInps           Set of input error gradient values passed to this layer from connected OutputListenrs during the learning phase.
protected  double[]	gradientOuts           Set of output error gradient values passed from this layer to connected InputListenrs during the learning phase.
protected  double[]	inps           Set of input values passed to this layer from connected InputListeners during the recall phase.
protected  java.util.Vector	inputPatternListeners           Contains the list of input connected listeners (InputPatternListener)
private  java.lang.String	LayerName           The name of the layer
protected  boolean	learnable           Contains true if for the Layer must be used a Learner instead of a built-in learning algorithm.
protected  boolean	learning           The Net's phase: false == recall; true == learning
private static org.joone.log.ILogger	log           Logger for this class
protected  int	m_batch           Not used but maintained for backward serialization compatability.
protected  Monitor	monitor           The monitor of the layer.
protected  Learner	myLearner           The Learner for this layer.
private  java.lang.Thread	myThread           The execution Thread for this layer.
private  java.lang.Object	myThreadMonitor           The monitor used to control read/write access to myThread
protected  java.util.Vector	outputPatternListeners           Contains the list of output connected listeners (OutputPatternListener)
protected  double[]	outs           Set of output values passed from this layer to connected OutputListeners durng the recall phase.
private  int	rows           The number of neurons in the layer
protected  boolean	running           Whether the layer is running
private static long	serialVersionUID           Serial version ID for this class
protected  int	step           The step number of the network run.
static int	STOP_FLAG           Stop flag.

 

Constructor Summary

Layer()           The empty constructor

Layer(java.lang.String ElemName)           Creates a named layer

 

Method Summary
boolean	addInputSynapse(InputPatternListener newListener)           Adds a new input synapse to the layer
void	addNoise(double amplitude)           Adds a noise componentto the biases of the layer and to all the input connected synapses.
boolean	addOutputSynapse(OutputPatternListener newListener)           Adds a new output synapse to the layer
protected  void	adjustSizeToFwdPattern(double[] aPattern)           Adjusts the size of a layer if the size of the forward pattern differs.
protected  void	adjustSizeToRevPattern(double[] aPattern)           Adjusts the size of a layer if the size of the reverse pattern differs.
protected abstract  void	backward(double[] pattern)           Reverse transfer function of the component.
java.util.TreeSet	check()           Get check messages from listeners.
protected  boolean	checkInputEnabled()           Checks if at least one input synapse is enabled
protected  boolean	checkInputs(java.util.Vector inputListeners)           Determine whether ther are any stream input synapses attached.
protected  boolean	checkOutputs(java.util.Vector outputListeners)           Determine whether ther are any stream output or teach synapses attached.
void	cicleTerminated(NeuralNetEvent e)           Not implemented.
NeuralLayer	copyInto(NeuralLayer newLayer)           Copies one layer into another, to obtain a type-transformation from one kind of Layer to another.
void	errorChanged(NeuralNetEvent e)           Not implemented.
void	finalize()           Method to help remove disused references quickly when the layer goes out of scope.
protected  void	fireFwdGet()           Calls all the fwdGet methods on the input synapses to get the input patterns
protected  void	fireFwdPut(Pattern pattern)           Calls all the fwdPut methods on the output synapses to pass them the calculated patterns
protected  void	fireRevGet()           Calls all the revGet methods on the output synapses to get the error gradients
protected  void	fireRevPut(Pattern pattern)           Calls all the revPut methods on the input synapses to get the input patterns and pass them the resulting calculated gradients
protected abstract  void	forward(double[] pattern)           Transfer function to recall a result on a trained net
java.util.Vector	getAllInputs()           Returns the vector of the input listeners
java.util.Vector	getAllOutputs()           Returns the vector of the output listeners
Matrix	getBias()           Return the bias matrix
int	getDimension()           Returns the number of neurons contained in the layer
double[]	getLastOutputs()           Gets the values lastly outputed by the neurons of this layer.
java.lang.String	getLayerName()           Returns the name of the layer
Learner	getLearner()           Returns the appropriate Learner object for this class depending on the Monitor.learningMode property value
Monitor	getMonitor()           Returns the monitor object
int	getRows()           Returns the dimension (# of neurons) of the Layer
protected  java.lang.Object	getThreadMonitor()           Getter for property myThreadMonitor.
boolean	hasStepCounter()           Determine whether this layer has an input synapse attached that is a step counter.
void	init()
void	initLearner()           Initialize the Learner object of this layer
java.lang.String	InspectableTitle()           Get the title for the inspectable interface
java.util.Collection	Inspections()           Method to get a collection of bias inspections for this layer
boolean	isInputLayer()           Determine whether this is an input layer.
boolean	isOutputLayer()           Determine whether this is an output layer.
boolean	isRunning()           Determine whether the execution thread is running
void	join()           Waits for the current layer's thread to stop
void	netStarted(NeuralNetEvent e)           Not implemented.
void	netStopped(NeuralNetEvent e)           Not implemented.
void	netStoppedError(NeuralNetEvent e, java.lang.String error)           Stops the execution thread and resets this layer in the event of an crtitical network error.
void	randomize(double amplitude)           Initialize the weights of the biases and of all the connected synapses
private  void	readObject(java.io.ObjectInputStream in)           Read in a serialised version of this layer
private  java.util.Vector	readVector(java.io.ObjectInputStream in)           Create a Vector from a serialized version
void	removeAllInputs()           Remove all the input listeners of the layer
void	removeAllOutputs()           Remove all the output listeners of the layer
void	removeInputSynapse(InputPatternListener newListener)           Remove an input Listener
void	removeOutputSynapse(OutputPatternListener newListener)           Remove an output listener from the layer
protected  void	resetInputListeners()           Reset all the input listeners
void	run()           The core running engine of the layer.
void	setAllInputs(java.util.Vector newInputPatternListeners)           Sets the Vector that contains all the input listeners.
void	setAllOutputs(java.util.Vector newOutputPatternListeners)           Sets the Vector that contains all the output listeners.
void	setBias(Matrix newBias)           Sets the matrix of biases
protected  void	setConnDimensions()           Sets the input and output synapses' dimensions
protected abstract  void	setDimensions()           Sets the dimension of the layer.
protected  void	setInputDimension(InputPatternListener syn)           Sets the dimension of the listener passed as parameter.
void	setInputSynapses(java.util.ArrayList newInputPatternListeners)           Sets the Vector that contains all the input listeners.
void	setLayerName(java.lang.String newLayerName)           Sets the name of the layer
void	setMonitor(Monitor mon)           Sets the monitor object
protected  void	setOutputDimension(OutputPatternListener syn)           Sets the dimension of the listener passed as parameter.
void	setOutputSynapses(java.util.ArrayList newOutputPatternListeners)           Sets the Vector that contains all the output listeners.
void	setRows(int newRows)           Sets the dimension (# of neurons) of the Layer
private  void	setVectMonitor(java.util.Vector vect, Monitor mon)           Set the monitor object for all pattern listeners in a Vector
void	start()           Starts the Layer
void	stop()           Stops the Layer
protected  void	sumBackInput(double[] pattern)           Calculates the net input of the error gradents during the learning phase
protected  void	sumInput(double[] pattern)           Calculates the net input of the values in the recall phase
java.lang.String	toString()           Produce a String representation of this layer
private  void	writeObject(java.io.ObjectOutputStream out)           Write a serialized version of this layer
private  void	writeVector(java.io.ObjectOutputStream out, java.util.Vector vect)           This method is useful to serialize only the vector's elements that don't implement the Serialize interface, only when the Monitor.isExporting returns the value TRUE.

 

Methods inherited from class java.lang.Object

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

 

Field Detail

STOP_FLAG

public static final int STOP_FLAG

Stop flag. If the step has this value, the execution thread terminates.

See Also:

Constant Field Values

---

serialVersionUID

private static final long serialVersionUID

Serial version ID for this class

See Also:

Constant Field Values

---

LayerName

private java.lang.String LayerName

The name of the layer

---

rows

private int rows

The number of neurons in the layer

---

bias

protected Matrix bias

Holds the bias of neurons of the layer

---

monitor

protected Monitor monitor

The monitor of the layer. Contains all parameters needed to the learning phase

---

m_batch

protected int m_batch

Not used but maintained for backward serialization compatability.

---

learning

protected boolean learning

The Net's phase: false == recall; true == learning

---

learnable

protected boolean learnable

Contains true if for the Layer must be used a Learner instead of a built-in learning algorithm. Set it in the constructor of any inherited class. Used by the getLearner method.

See Also:

getLearner

---

inputPatternListeners

protected java.util.Vector inputPatternListeners

Contains the list of input connected listeners (InputPatternListener)

---

outputPatternListeners

protected java.util.Vector outputPatternListeners

Contains the list of output connected listeners (OutputPatternListener)

---

myThread

private transient java.lang.Thread myThread

The execution Thread for this layer.

---

myThreadMonitor

private transient java.lang.Object myThreadMonitor

The monitor used to control read/write access to myThread

---

outs

protected transient double[] outs

Set of output values passed from this layer to connected OutputListeners durng the recall phase.

---

inps

protected transient double[] inps

Set of input values passed to this layer from connected InputListeners during the recall phase.

---

gradientInps

protected transient double[] gradientInps

Set of input error gradient values passed to this layer from connected OutputListenrs during the learning phase.

---

gradientOuts

protected transient double[] gradientOuts

Set of output error gradient values passed from this layer to connected InputListenrs during the learning phase.

---

step

protected transient int step

The step number of the network run.

---

running

protected transient boolean running

Whether the layer is running

---

myLearner

protected transient Learner myLearner

The Learner for this layer.

---

log

private static final org.joone.log.ILogger log

Logger for this class

Constructor Detail

Layer

public Layer()

The empty constructor

---

Layer

public Layer(java.lang.String ElemName)

Creates a named layer

Method Detail

addNoise

public void addNoise(double amplitude)

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

Specified by:

addNoise in interface NeuralLayer

---

randomize

public void randomize(double amplitude)

Initialize the weights of the biases and of all the connected synapses

---

backward

protected abstract void backward(double[] pattern)
                          throws org.joone.exception.JooneRuntimeException

Reverse transfer function of the component.

---

copyInto

public NeuralLayer copyInto(NeuralLayer newLayer)

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

Specified by:

copyInto in interface NeuralLayer

---

fireFwdGet

protected void fireFwdGet()

Calls all the fwdGet methods on the input synapses to get the input patterns

---

fireFwdPut

protected void fireFwdPut(Pattern pattern)

Calls all the fwdPut methods on the output synapses to pass them the calculated patterns

---

fireRevGet

protected void fireRevGet()

Calls all the revGet methods on the output synapses to get the error gradients

---

fireRevPut

protected void fireRevPut(Pattern pattern)

Calls all the revPut methods on the input synapses to get the input patterns and pass them the resulting calculated gradients

---

adjustSizeToFwdPattern

protected void adjustSizeToFwdPattern(double[] aPattern)

Adjusts the size of a layer if the size of the forward pattern differs.

---

adjustSizeToRevPattern

protected void adjustSizeToRevPattern(double[] aPattern)

Adjusts the size of a layer if the size of the reverse pattern differs.

---

forward

protected abstract void forward(double[] pattern)
                         throws org.joone.exception.JooneRuntimeException

Transfer function to recall a result on a trained net

---

getAllInputs

public java.util.Vector getAllInputs()

Returns the vector of the input listeners

Specified by:

getAllInputs in interface NeuralLayer

---

getAllOutputs

public java.util.Vector getAllOutputs()

Returns the vector of the output listeners

Specified by:

getAllOutputs in interface NeuralLayer

---

getBias

public Matrix getBias()

Return the bias matrix

Specified by:

getBias in interface NeuralLayer

---

getDimension

public int getDimension()

Returns the number of neurons contained in the layer

---

getLayerName

public java.lang.String getLayerName()

Returns the name of the layer

Specified by:

getLayerName in interface NeuralLayer

---

getMonitor

public Monitor getMonitor()

Returns the monitor object

Specified by:

getMonitor in interface NeuralLayer

---

getRows

public int getRows()

Returns the dimension (# of neurons) of the Layer

Specified by:

getRows in interface NeuralLayer

---

removeAllInputs

public void removeAllInputs()

Remove all the input listeners of the layer

Specified by:

removeAllInputs in interface NeuralLayer

---

removeAllOutputs

public void removeAllOutputs()

Remove all the output listeners of the layer

Specified by:

removeAllOutputs in interface NeuralLayer

---

removeInputSynapse

public void removeInputSynapse(InputPatternListener newListener)

Remove an input Listener

Specified by:

removeInputSynapse in interface NeuralLayer

---

removeOutputSynapse

public void removeOutputSynapse(OutputPatternListener newListener)

Remove an output listener from the layer

Specified by:

removeOutputSynapse in interface NeuralLayer

---

getLastOutputs

public double[] getLastOutputs()

Gets the values lastly outputed by the neurons of this layer.

---

run

public void run()
         throws org.joone.exception.JooneRuntimeException

The core running engine of the layer. Called from the method start()

Specified by:

run in interface java.lang.Runnable

---

setAllInputs

public void setAllInputs(java.util.Vector newInputPatternListeners)

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

Specified by:

setAllInputs in interface NeuralLayer

---

setInputSynapses

public void setInputSynapses(java.util.ArrayList newInputPatternListeners)

Sets the Vector that contains all the input listeners. It accepts an ArrayList as parameter. Added for Spring Can be useful to set the input synapses taken from another Layer

---

setAllOutputs

public void setAllOutputs(java.util.Vector newOutputPatternListeners)

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

Specified by:

setAllOutputs in interface NeuralLayer

---

setOutputSynapses

public void setOutputSynapses(java.util.ArrayList newOutputPatternListeners)

Sets the Vector that contains all the output listeners. It accepts an ArrayList as parameter. Added for Spring Can be useful to set the output synapses taken from another Layer

---

setBias

public void setBias(Matrix newBias)

Sets the matrix of biases

Specified by:

setBias in interface NeuralLayer

---

setDimensions

protected abstract void setDimensions()

Sets the dimension of the layer. Override to define how the internal buffers must be sized.

---

setInputDimension

protected void setInputDimension(InputPatternListener syn)

Sets the dimension of the listener passed as parameter. Called after a new input listener is added.

---

addInputSynapse

public boolean addInputSynapse(InputPatternListener newListener)

Adds a new input synapse to the layer

Specified by:

addInputSynapse in interface NeuralLayer

---

setLayerName

public void setLayerName(java.lang.String newLayerName)

Sets the name of the layer

Specified by:

setLayerName in interface NeuralLayer

---

setMonitor

public void setMonitor(Monitor mon)

Sets the monitor object

Specified by:

setMonitor in interface NeuralLayer

---

setVectMonitor

private void setVectMonitor(java.util.Vector vect,
                            Monitor mon)

Set the monitor object for all pattern listeners in a Vector

---

setOutputDimension

protected void setOutputDimension(OutputPatternListener syn)

Sets the dimension of the listener passed as parameter. Called after a new output listener is added.

---

addOutputSynapse

public boolean addOutputSynapse(OutputPatternListener newListener)

Adds a new output synapse to the layer

Specified by:

addOutputSynapse in interface NeuralLayer

---

setRows

public void setRows(int newRows)

Sets the dimension (# of neurons) of the Layer

Specified by:

setRows in interface NeuralLayer

---

start

public void start()

Starts the Layer

Specified by:

start in interface NeuralLayer

---

init

public void init()

---

checkInputEnabled

protected boolean checkInputEnabled()

Checks if at least one input synapse is enabled

---

stop

public void stop()

Stops the Layer

---

resetInputListeners

protected void resetInputListeners()

Reset all the input listeners

---

sumBackInput

protected void sumBackInput(double[] pattern)

Calculates the net input of the error gradents during the learning phase

---

sumInput

protected void sumInput(double[] pattern)

Calculates the net input of the values in the recall phase

---

readObject

private void readObject(java.io.ObjectInputStream in)
                 throws java.io.IOException,
                        java.lang.ClassNotFoundException

Read in a serialised version of this layer

---

writeObject

private void writeObject(java.io.ObjectOutputStream out)
                  throws java.io.IOException

Write a serialized version of this layer

---

writeVector

private void writeVector(java.io.ObjectOutputStream out,
                         java.util.Vector vect)
                  throws java.io.IOException

This method is useful to serialize only the vector's elements that don't implement the Serialize interface, only when the Monitor.isExporting returns the value TRUE.

---

readVector

private java.util.Vector readVector(java.io.ObjectInputStream in)
                             throws java.io.IOException,
                                    java.lang.ClassNotFoundException

Create a Vector from a serialized version

---

setConnDimensions

protected void setConnDimensions()

Sets the input and output synapses' dimensions

---

isRunning

public boolean isRunning()

Determine whether the execution thread is running

Specified by:

isRunning in interface NeuralLayer

---

check

public java.util.TreeSet check()

Get check messages from listeners. Subclasses should call this method from thier own check method.

Specified by:

check in interface NeuralLayer

---

toString

public java.lang.String toString()

Produce a String representation of this layer

---

finalize

public void finalize()
              throws java.lang.Throwable

Method to help remove disused references quickly when the layer goes out of scope.

---

Inspections

public java.util.Collection Inspections()

Method to get a collection of bias inspections for this layer

Specified by:

Inspections in interface org.joone.inspection.Inspectable

---

InspectableTitle

public java.lang.String InspectableTitle()

Get the title for the inspectable interface

Specified by:

InspectableTitle in interface org.joone.inspection.Inspectable

---

hasStepCounter

public boolean hasStepCounter()

Determine whether this layer has an input synapse attached that is a step counter.

---

isInputLayer

public boolean isInputLayer()

Determine whether this is an input layer.

---

checkInputs

protected boolean checkInputs(java.util.Vector inputListeners)

Determine whether ther are any stream input synapses attached.

---

isOutputLayer

public boolean isOutputLayer()

Determine whether this is an output layer.

---

checkOutputs

protected boolean checkOutputs(java.util.Vector outputListeners)

Determine whether ther are any stream output or teach synapses attached. Also checks the attached listeners of OutputSwitchSynapses. Also checks for loopback condition. All connected synapses must be of this type.

---

netStarted

public void netStarted(NeuralNetEvent e)

Not implemented.

Specified by:

netStarted in interface NeuralNetListener

---

cicleTerminated

public void cicleTerminated(NeuralNetEvent e)

Not implemented.

Specified by:

cicleTerminated in interface NeuralNetListener

---

netStopped

public void netStopped(NeuralNetEvent e)

Not implemented.

Specified by:

netStopped in interface NeuralNetListener

---

errorChanged

public void errorChanged(NeuralNetEvent e)

Not implemented.

Specified by:

errorChanged in interface NeuralNetListener

---

netStoppedError

public void netStoppedError(NeuralNetEvent e,
                            java.lang.String error)

Stops the execution thread and resets this layer in the event of an crtitical network error.

Specified by:

netStoppedError in interface NeuralNetListener

---

getLearner

public Learner getLearner()

Returns the appropriate Learner object for this class depending on the Monitor.learningMode property value

Specified by:

getLearner in interface Learnable

---

initLearner

public void initLearner()

Initialize the Learner object of this layer

Specified by:

initLearner in interface Learnable

---

getThreadMonitor

protected java.lang.Object getThreadMonitor()

Getter for property myThreadMonitor.

---

join

public void join()

Waits for the current layer's thread to stop

---

Overview  Package   Class  Use  Deprecated  Index
Home >> All >> org >> joone >> [ engine overview ]	PREV CLASS  NEXT CLASS
SUMMARY:  JAVADOC |  SOURCE |  DOWNLOAD | NESTED | FIELD | CONSTR | METHOD	DETAIL: FIELD | CONSTR | METHOD

---