org.joone.engine.learning
Class ComparingSynapse

java.lang.Object
  org.joone.engine.learning.ComparingSynapse

All Implemented Interfaces:

java.io.Serializable, ComparingElement, NeuralElement, OutputPatternListener

public class ComparingSynapse
extends java.lang.Object
implements ComparingElement

See Also:

Serialized Form

Constructor Summary

ComparingSynapse()

Method Summary

boolean	addResultSynapse(OutputPatternListener listener) Adds an output synapse to which the result must be sent
protected void	backward(double[] pattern) Training phase.
java.util.TreeSet	check() Validation checks for invalid parameter values, misconfiguration, etc.
protected void	forward(double[] pattern) Recall phase
void	fwdPut(Pattern pattern) Method to put a pattern forward to the next layer
StreamInputSynapse	getDesired() Insert the method's description here.
int	getInputDimension() getInputDimension method comment.
Monitor	getMonitor() Insert the method's description here.
java.lang.String	getName() Returns the name of the output synapse
ComparisonSynapse	getTheComparisonSynapse()
LinearLayer	getTheLinearLayer() Returns the internal Layer used to transport the result to the connected output synapse
void	init()
boolean	isEnabled() Getter for property enabled.
boolean	isOutputFull() Getter for property outputFull.
void	removeResultSynapse(OutputPatternListener listener) Removes an output synapse
void	reset() Less intense than resetInput
void	resetInput() Resets the internal buffer of the desired StreamInputSynapse
Pattern	revGet() Returns the error pattern coming from the next layer during the training phase
protected void	setArrays(int rows, int cols) Insert the method's description here.
boolean	setDesired(StreamInputSynapse fn) Setter for the desired data set
protected void	setDimensions(int rows, int cols)
void	setEnabled(boolean enabled) Setter for property enabled.
void	setInputDimension(int newInputDimension) setInputDimension method.
void	setMonitor(Monitor newMonitor) Data di creazione: (06/04/00 23.33.24)
void	setName(java.lang.String newName) Sets the name of the output synapse
void	setOutputFull(boolean outputFull) Setter for property outputFull.
void	setTheComparisonSynapse(ComparisonSynapse theComparisonSynapse) Needed for Save as XML
void	setTheLinearLayer(LinearLayer newTheLinearLayer) Needed for Save as XML
void	stop()

Methods inherited from class java.lang.Object

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

Constructor Detail

ComparingSynapse

public ComparingSynapse()

Method Detail

fwdPut

public void fwdPut(Pattern pattern)

Description copied from interface: OutputPatternListener

Method to put a pattern forward to the next layer

Specified by:

fwdPut in interface OutputPatternListener

Parameters:

pattern - neural.engine.Pattern

getDesired

public StreamInputSynapse getDesired()

Insert the method's description here. Creation date: (03/08/2000 22.50.55)

Specified by:

getDesired in interface ComparingElement

Returns:

java.lang.String

getInputDimension

public int getInputDimension()

getInputDimension method comment.

Specified by:

getInputDimension in interface OutputPatternListener

Returns:

int

getMonitor

public Monitor getMonitor()

Insert the method's description here. Creation date: (03/08/2000 22.54.48)

Specified by:

getMonitor in interface NeuralElement

Returns:

neural.engine.Monitor

getTheLinearLayer

public LinearLayer getTheLinearLayer()

Description copied from interface: ComparingElement

Returns the internal Layer used to transport the result to the connected output synapse

Specified by:

getTheLinearLayer in interface ComparingElement

Returns:

neural.engine.LinearLayer changed to public for Save As XML

getTheComparisonSynapse

public ComparisonSynapse getTheComparisonSynapse()

Returns:

neural.engine.TeacherSynapse changed to public for Save As XML

revGet

public Pattern revGet()

Description copied from interface: OutputPatternListener

Returns the error pattern coming from the next layer during the training phase

Specified by:

revGet in interface OutputPatternListener

Returns:

neural.engine.Pattern

setDesired

public boolean setDesired(StreamInputSynapse fn)

Description copied from interface: ComparingElement

Setter for the desired data set

Specified by:

setDesired in interface ComparingElement

addResultSynapse

public boolean addResultSynapse(OutputPatternListener listener)

Description copied from interface: ComparingElement

Adds an output synapse to which the result must be sent

Specified by:

addResultSynapse in interface ComparingElement

removeResultSynapse

public void removeResultSynapse(OutputPatternListener listener)

Description copied from interface: ComparingElement

Removes an output synapse

Specified by:

removeResultSynapse in interface ComparingElement

setInputDimension

public void setInputDimension(int newInputDimension)

setInputDimension method.

Specified by:

setInputDimension in interface OutputPatternListener

setMonitor

public void setMonitor(Monitor newMonitor)

Data di creazione: (06/04/00 23.33.24)

Specified by:

setMonitor in interface NeuralElement

Parameters:

newMonitor - neural.engine.Monitor

stop

public void stop()

getName

public java.lang.String getName()

Description copied from interface: NeuralElement

Returns the name of the output synapse

Specified by:

getName in interface NeuralElement

Returns:

String

setName

public void setName(java.lang.String newName)

Description copied from interface: NeuralElement

Sets the name of the output synapse

Specified by:

setName in interface NeuralElement

Parameters:

newName - String

forward

protected void forward(double[] pattern)

Recall phase

Parameters:

pattern - double[] - pattern di input sul quale applicare la funzione di trasferimento

setArrays

protected void setArrays(int rows,
                         int cols)

Insert the method's description here. Creation date: (23/09/2000 12.52.58)

setDimensions

protected void setDimensions(int rows,
                             int cols)

Parameters:

int - rows - righe

int - cols - colonne

backward

protected void backward(double[] pattern)

Training phase.

Parameters:

pattern - double[] - input pattern

setTheComparisonSynapse

public void setTheComparisonSynapse(ComparisonSynapse theComparisonSynapse)

Needed for Save as XML

setTheLinearLayer

public void setTheLinearLayer(LinearLayer newTheLinearLayer)

Needed for Save as XML

resetInput

public void resetInput()

Description copied from interface: ComparingElement

Resets the internal buffer of the desired StreamInputSynapse

Specified by:

resetInput in interface ComparingElement

reset

public void reset()

Less intense than resetInput

Specified by:

reset in interface ComparingElement

check

public java.util.TreeSet check()

Description copied from interface: NeuralElement

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.

Specified by:

check in interface NeuralElement

Returns:

validation errors.

isEnabled

public boolean isEnabled()

Getter for property enabled.

Specified by:

isEnabled in interface NeuralElement

Returns:

Value of property enabled.

setEnabled

public void setEnabled(boolean enabled)

Setter for property enabled.

Specified by:

setEnabled in interface NeuralElement

Parameters:

enabled - New value of property enabled.

isOutputFull

public boolean isOutputFull()

Getter for property outputFull.

Specified by:

isOutputFull in interface OutputPatternListener

Returns:

Value of property outputFull.

setOutputFull

public void setOutputFull(boolean outputFull)

Setter for property outputFull.

Specified by:

setOutputFull in interface OutputPatternListener

Parameters:

outputFull - New value of property outputFull.

init

public void init()

Specified by:

init in interface NeuralElement