org.encog.neural.networks.training.anneal
Class NeuralTrainingSetSimulatedAnnealing

java.lang.Object
  org.encog.neural.networks.training.BasicTraining
      org.encog.neural.networks.training.anneal.NeuralSimulatedAnnealing
          org.encog.neural.networks.training.anneal.NeuralTrainingSetSimulatedAnnealing

All Implemented Interfaces:

Train

public class NeuralTrainingSetSimulatedAnnealing
extends NeuralSimulatedAnnealing

A simulated annealing implementation that trains from a training set.

Field Summary

Fields inherited from class org.encog.neural.networks.training.anneal.NeuralSimulatedAnnealing

CUT

Constructor Summary

NeuralTrainingSetSimulatedAnnealing(BasicNetwork network, NeuralDataSet training, double startTemp, double stopTemp, int cycles)
Construct a simulated annealing object to train a network with a training set.

Method Summary

double

determineError() Determine the error of the current weights and thresholds.

Methods inherited from class org.encog.neural.networks.training.anneal.NeuralSimulatedAnnealing

getArray, getArrayCopy, getNetwork, iteration, putArray, randomize

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

NeuralTrainingSetSimulatedAnnealing

public NeuralTrainingSetSimulatedAnnealing(BasicNetwork network,
                                           NeuralDataSet training,
                                           double startTemp,
                                           double stopTemp,
                                           int cycles)

Construct a simulated annealing object to train a network with a training set.

Parameters:

network - The network to train.

training - The training set to use.

startTemp - The starting temperature.

stopTemp - The ending temperature.

cycles - The number of cycles per iteration.

Method Detail

determineError

public double determineError()

Determine the error of the current weights and thresholds.

Specified by:

determineError in class NeuralSimulatedAnnealing

Returns:

The error.