org.joone.net

Class NeuralNetValidator

java.lang.Object

org.joone.net.NeuralNetValidator

All Implemented Interfaces:

java.lang.Runnable, java.util.EventListener, NeuralNetListener

public class NeuralNetValidator
extends java.lang.Object
implements java.lang.Runnable, NeuralNetListener

This class is useful to validate a neural network. It simply sets some parameters of the neural network passed as parameter and starts itself in a separated thread, notifying a listener when the validation step finishes.

Author:

pmarrone

Constructor Summary

Constructors

Constructor and Description
NeuralNetValidator(NeuralNet nn)

Method Summary

Methods

Modifier and Type	Method and Description
void	addValidationListener(NeuralValidationListener newListener)
void	cicleTerminated(NeuralNetEvent e)
void	errorChanged(NeuralNetEvent e)
void	fireNetValidated()
NeuralNet	getNeuralNet() Gets the network to validate (or has been validated).
void	netStarted(NeuralNetEvent e)
void	netStopped(NeuralNetEvent e)
void	netStoppedError(NeuralNetEvent e, java.lang.String error)
void	run()
void	start() Starts the validation into a separated thread
void	useTrainingData(boolean anUse) By default the validator validates a neural network with validation data, however by calling this method before calling the start() method, one can decide if the network should be validated with validation data (the parameter anUse should be false) or by using the training data (the parameter anUse should be true).
protected void	validate()

Methods inherited from class java.lang.Object

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

Constructor Detail

NeuralNetValidator

public NeuralNetValidator(NeuralNet nn)

Method Detail

addValidationListener

public void addValidationListener(NeuralValidationListener newListener)

validate

protected void validate()

fireNetValidated

public void fireNetValidated()

useTrainingData

public void useTrainingData(boolean anUse)

By default the validator validates a neural network with validation data, however by calling this method before calling the start() method, one can decide if the network should be validated with validation data (the parameter anUse should be false) or by using the training data (the parameter anUse should be true).

Parameters:

anUse - true if we should use training data for validation, false if we should use the validation data for validation (default).

start

public void start()

Starts the validation into a separated thread

run

public void run()

Specified by:

run in interface java.lang.Runnable

netStopped

public void netStopped(NeuralNetEvent e)

Specified by:

netStopped in interface NeuralNetListener

cicleTerminated

public void cicleTerminated(NeuralNetEvent e)

Specified by:

cicleTerminated in interface NeuralNetListener

netStarted

public void netStarted(NeuralNetEvent e)

Specified by:

netStarted in interface NeuralNetListener

errorChanged

public void errorChanged(NeuralNetEvent e)

Specified by:

errorChanged in interface NeuralNetListener

netStoppedError

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

Specified by:

netStoppedError in interface NeuralNetListener

getNeuralNet

public NeuralNet getNeuralNet()

Gets the network to validate (or has been validated).

Returns:

the netork to validate (or the network that has been validated).