org.generation5.nn
Class KohonenTrainer

java.lang.Object
  org.generation5.nn.NeuralNetworkTrainer
      org.generation5.nn.KohonenTrainer

All Implemented Interfaces:

Steppable

public abstract class KohonenTrainer

extends NeuralNetworkTrainer

This class implements the Kohonen training algorithm. The class implements the training algorithm as a two-stage process: phase one reduces the neighbourhood radius slowly to one, while the learning constant k is reduced from 0.9 to 0.1. Phase two increases the number of training points slightly, keeps the neighbourhood size constant at one, and reduces the learning rate from 0.1 to 0.

Field Summary

protected int	currentIteration The current training iteration.
protected double	deltaK The amount at which k should be reduced.
protected boolean	hasFinished Denotes whether the network has finished training.
protected KohonenNN	kohonenNN The Kohonen network.
protected int	phaseOne The number of phase one training iterations.
protected int	phaseTwo The number of phase two training iterations.
protected int	reductionStep The number of iterations to train before reducing the neighbourhood size.
protected double[]	trainData The training data.
protected int	trainingSteps The training steps per iteration.

Fields inherited from class org.generation5.nn.NeuralNetworkTrainer

notifier

Constructor Summary

KohonenTrainer()
Creates a new instance of KohonenTrainer

Method Summary

void	doStep() Iterates one step of the Kohonen training algorithm.
int	getCurrentIteration() Returns the current iteration.
NeuralNetwork	getNetwork() Return the network being used.
int	getPhase() Return the phase being used by the Kohonen network (1 or 2).
abstract double[]	getTrainingPoint() Abstract method to allow a deriving class to return a valid training point.
void	init() Initializes the trainer.
boolean	isComplete() Returns whether the training is complete (hasFinished).
void	setNetwork(NeuralNetwork net) Set the Kohonen network to use in the trainer.
void	setPhases(int p1, int p2) Set the number of iterations for the two training phases.

Methods inherited from class org.generation5.nn.NeuralNetworkTrainer

reset, run, setNotifier

Methods inherited from class java.lang.Object

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

Field Detail

phaseOne

protected int phaseOne

The number of phase one training iterations.

phaseTwo

protected int phaseTwo

The number of phase two training iterations.

trainingSteps

protected int trainingSteps

The training steps per iteration.

reductionStep

protected int reductionStep

The number of iterations to train before reducing the neighbourhood size.

currentIteration

protected int currentIteration

The current training iteration.

deltaK

protected double deltaK

The amount at which k should be reduced.

trainData

protected double[] trainData

The training data.

hasFinished

protected boolean hasFinished

Denotes whether the network has finished training.

kohonenNN

protected KohonenNN kohonenNN

The Kohonen network.

Constructor Detail

KohonenTrainer

public KohonenTrainer()

Creates a new instance of KohonenTrainer

Method Detail

setPhases

public void setPhases(int p1,
                      int p2)

Set the number of iterations for the two training phases.

Parameters:

p1 - the number of phase one iterations.

p2 - the number of phase two iterations.

getTrainingPoint

public abstract double[] getTrainingPoint()

Abstract method to allow a deriving class to return a valid training point.

Returns:

Returns a random training point.

doStep

public void doStep()

Iterates one step of the Kohonen training algorithm. Nofitications are set up to fire after every iteration (ID = 0), and once training has completed (ID = 1). For more information about the training algorithm itself, see the class description.

Specified by:

doStep in interface Steppable

Specified by:

doStep in class NeuralNetworkTrainer

init

public void init()

Initializes the trainer.

Specified by:

init in interface Steppable

Specified by:

init in class NeuralNetworkTrainer

setNetwork

public void setNetwork(NeuralNetwork net)

Set the Kohonen network to use in the trainer.

Specified by:

setNetwork in class NeuralNetworkTrainer

Parameters:

net - the Kohonen network to use.

getNetwork

public NeuralNetwork getNetwork()

Return the network being used.

Specified by:

getNetwork in class NeuralNetworkTrainer

Returns:

the network being used.

isComplete

public boolean isComplete()

Returns whether the training is complete (hasFinished).

Specified by:

isComplete in class NeuralNetworkTrainer

Returns:

true if training has completeld, otherwise false.

See Also:

hasFinished

getCurrentIteration

public int getCurrentIteration()

Returns the current iteration.

Returns:

the current iteration.

getPhase

public int getPhase()

Return the phase being used by the Kohonen network (1 or 2).

Returns:

the phase the Kohonen training algorithm is in.