org.encog.neural.networks.training.genetic
Class TrainingSetNeuralGeneticAlgorithm

java.lang.Object
  org.encog.solve.genetic.GeneticAlgorithm<java.lang.Double>
      org.encog.neural.networks.training.genetic.NeuralGeneticAlgorithm
          org.encog.neural.networks.training.genetic.TrainingSetNeuralGeneticAlgorithm

public class TrainingSetNeuralGeneticAlgorithm
extends NeuralGeneticAlgorithm

TrainingSetNeuralGeneticAlgorithm: Implements a genetic algorithm that allows a feedforward neural network to be trained using a genetic algorithm. This algorithm is for a feed forward neural network. The neural network is trained using training sets.

Field Summary

Fields inherited from class org.encog.solve.genetic.GeneticAlgorithm

TIMEOUT

Constructor Summary

TrainingSetNeuralGeneticAlgorithm(BasicNetwork network, boolean reset, NeuralDataSet training, int populationSize, double mutationPercent, double percentToMate)
Construct a training object.

Method Summary

double	getError() Returns the root mean square error for a complet training set.
NeuralDataSet	getTraining()

Methods inherited from class org.encog.neural.networks.training.genetic.NeuralGeneticAlgorithm

getNetwork

Methods inherited from class org.encog.solve.genetic.GeneticAlgorithm

getChromosome, getChromosomes, getCutLength, getMatingPopulation, getMutationPercent, getPercentToMate, getPool, getPopulationSize, isPreventRepeat, iteration, setChromosome, setChromosomes, setCutLength, setMatingPopulation, setMutationPercent, setPercentToMate, setPool, setPopulationSize, setPreventRepeat, sortChromosomes

Methods inherited from class java.lang.Object

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

Constructor Detail

TrainingSetNeuralGeneticAlgorithm

public TrainingSetNeuralGeneticAlgorithm(BasicNetwork network,
                                         boolean reset,
                                         NeuralDataSet training,
                                         int populationSize,
                                         double mutationPercent,
                                         double percentToMate)

Construct a training object.

Parameters:

network - The network to train.

reset - Should each chromosome be reset.

training - The training set.

populationSize - The population size.

mutationPercent - The mutation percent.

percentToMate - The percent to mate.

Method Detail

getError

public double getError()

Returns the root mean square error for a complet training set.

Returns:

The current error for the neural network.

Throws:

NeuralNetworkException

getTraining

public NeuralDataSet getTraining()

Returns:

the training data