org.encog.neural.flat.train.prop
Class TrainFlatNetworkManhattan

java.lang.Object
  org.encog.neural.flat.train.prop.TrainFlatNetworkProp
      org.encog.neural.flat.train.prop.TrainFlatNetworkManhattan

All Implemented Interfaces:

TrainFlatNetwork

public class TrainFlatNetworkManhattan
extends TrainFlatNetworkProp

Train the flat network using Manhattan update rule.

Field Summary

Fields inherited from class org.encog.neural.flat.train.prop.TrainFlatNetworkProp

currentError, gradients, lastError, network

Constructor Summary

TrainFlatNetworkManhattan(FlatNetwork network, MLDataSet training, double theLearningRate)
Construct a trainer for flat networks to use the Manhattan update rule.

Method Summary

double	getLearningRate()
void	initOthers() Perform training method specific init.
void	setLearningRate(double theLearningRate)
double	updateWeight(double[] gradients, double[] lastGradient, int index) Calculate the amount to change the weight by.

Methods inherited from class org.encog.neural.flat.train.prop.TrainFlatNetworkProp

calculateGradients, finishTraining, fixFlatSpot, getError, getErrorFunction, getIteration, getLastGradient, getNetwork, getNumThreads, getTraining, iteration, iteration, learn, learnLimited, report, setErrorFunction, setIteration, setNumThreads

Methods inherited from class java.lang.Object

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

Constructor Detail

TrainFlatNetworkManhattan

public TrainFlatNetworkManhattan(FlatNetwork network,
                                 MLDataSet training,
                                 double theLearningRate)

Construct a trainer for flat networks to use the Manhattan update rule.

Parameters:

network - The network to train.

training - The training data to use.

theLearningRate - The learning rate to use.

Method Detail

getLearningRate

public final double getLearningRate()

Returns:

the learningRate

setLearningRate

public final void setLearningRate(double theLearningRate)

Parameters:

theLearningRate - the learningRate to set

updateWeight

public final double updateWeight(double[] gradients,
                                 double[] lastGradient,
                                 int index)

Calculate the amount to change the weight by.

Specified by:

updateWeight in class TrainFlatNetworkProp

Parameters:

gradients - The gradients.

lastGradient - The last gradients.

index - The index to update.

Returns:

The amount to change the weight by.

initOthers

public void initOthers()

Perform training method specific init.

Specified by:

initOthers in class TrainFlatNetworkProp