org.encog.neural.networks.training.competitive
Class CompetitiveTraining

java.lang.Object
  org.encog.neural.networks.training.BasicTraining
      org.encog.neural.networks.training.competitive.CompetitiveTraining

All Implemented Interfaces:

LearningRate, Train

public class CompetitiveTraining
extends BasicTraining
implements LearningRate

This class implements competitive training, which would be used in a winner-take-all neural network, such as the self organizing map (SOM). This is an unsupervised training method, no ideal data is needed on the training set. If ideal data is provided, it will be ignored. Training is done by looping over all of the training elements and calculating a "best matching unit" (BMU). This BMU output neuron is then adjusted to better "learn" this pattern. Additionally, this training may be applied to othr "nearby" output neurons. The degree to which nearby neurons are update is defined by the neighborhood function. A neighborhood function is required to determine the degree to which neighboring neurons (to the winning neuron) are updated by each training iteration. Because this is unsupervised training, calculating an error to measure progress by is difficult. The error is defined to be the "worst", or longest, Euclidean distance of any of the BMU's. This value should be minimized, as learning progresses. Because only the BMU neuron and its close neighbors are updated, you can end up with some output neurons that learn nothing. By default these neurons are forced to win patterns that are not represented well. This spreads out the workload among all output neurons. This feature is used by default, but can be disabled by setting the "forceWinner" property.

Author:

jheaton

Constructor Summary

CompetitiveTraining(BasicNetwork network, double learningRate, NeuralDataSet training, NeighborhoodFunction neighborhood)
Create an instance of competitive training.

Method Summary

int	getInputNeuronCount()
double	getLearningRate()
NeighborhoodFunction	getNeighborhood()
BasicNetwork	getNetwork() Get the current best network from the training.
int	getOutputNeuronCount()
boolean	isForceWinner()
void	iteration() Perform one training iteration.
void	setForceWinner(boolean forceWinner) Determine if a winner is to be forced.
void	setLearningRate(double rate) Set the learning rate.

Methods inherited from class org.encog.neural.networks.training.BasicTraining

addStrategy, finishTraining, getError, getStrategies, getTraining, postIteration, preIteration, setError, setTraining

Methods inherited from class java.lang.Object

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

Constructor Detail

CompetitiveTraining

public CompetitiveTraining(BasicNetwork network,
                           double learningRate,
                           NeuralDataSet training,
                           NeighborhoodFunction neighborhood)

Create an instance of competitive training.

Parameters:

network - The network to train.

learningRate - The learning rate, how much to apply per iteration.

training - The training set (unsupervised).

neighborhood - The neighborhood function to use.

Method Detail

getInputNeuronCount

public int getInputNeuronCount()

Returns:

The input neuron count.

getLearningRate

public double getLearningRate()

Specified by:

getLearningRate in interface LearningRate

Returns:

The learning rate. This was set when the object was created.

getNeighborhood

public NeighborhoodFunction getNeighborhood()

Returns:

The network neighborhood function.

getNetwork

public BasicNetwork getNetwork()

Description copied from interface: Train

Get the current best network from the training.

Specified by:

getNetwork in interface Train

Returns:

The network being trained.

getOutputNeuronCount

public int getOutputNeuronCount()

Returns:

The output neuron count.

isForceWinner

public boolean isForceWinner()

Returns:

Is a winner to be forced of neurons that do not learn. See class description for more info.

iteration

public void iteration()

Perform one training iteration.

Specified by:

iteration in interface Train

setForceWinner

public void setForceWinner(boolean forceWinner)

Determine if a winner is to be forced. See class description for more info.

Parameters:

forceWinner - True if a winner is to be forced.

setLearningRate

public void setLearningRate(double rate)

Set the learning rate. This is the rate at which the weights are changed.

Specified by:

setLearningRate in interface LearningRate

Parameters:

rate - The learning rate.