org.encog.neural.networks.training.propagation.back
Class Backpropagation

java.lang.Object
  extended by org.encog.ml.train.BasicTraining
      extended by org.encog.neural.networks.training.propagation.Propagation
          extended by org.encog.neural.networks.training.propagation.back.Backpropagation
All Implemented Interfaces:
MLTrain, BatchSize, LearningRate, Momentum, Train, MultiThreadable

public class Backpropagation
extends Propagation
implements Momentum, LearningRate

This class implements a backpropagation training algorithm for feed forward neural networks. It is used in the same manner as any other training class that implements the Train interface. Backpropagation is a common neural network training algorithm. It works by analyzing the error of the output of the neural network. Each neuron in the output layer's contribution, according to weight, to this error is determined. These weights are then adjusted to minimize this error. This process continues working its way backwards through the layers of the neural network. This implementation of the backpropagation algorithm uses both momentum and a learning rate. The learning rate specifies the degree to which the weight matrixes will be modified through each iteration. The momentum specifies how much the previous learning iteration affects the current. To use no momentum at all specify zero. One primary problem with backpropagation is that the magnitude of the partial derivative is often detrimental to the training of the neural network. The other propagation methods of Manhatten and Resilient address this issue in different ways. In general, it is suggested that you use the resilient propagation technique for most Encog training tasks over back propagation.


Field Summary
static String LAST_DELTA
          The resume key for backpropagation.
 
Fields inherited from class org.encog.neural.networks.training.propagation.Propagation
gradients, lastError, network
 
Constructor Summary
Backpropagation(ContainsFlat network, MLDataSet training)
          Create a class to train using backpropagation.
Backpropagation(ContainsFlat network, MLDataSet training, double theLearnRate, double theMomentum)
           
 
Method Summary
 boolean canContinue()
          
 double[] getLastDelta()
           
 double getLearningRate()
           
 double getMomentum()
           
 void initOthers()
          Perform training method specific init.
 boolean isValidResume(TrainingContinuation state)
          Determine if the specified continuation object is valid to resume with.
 TrainingContinuation pause()
          Pause the training.
 void resume(TrainingContinuation state)
          Resume training.
 void setLearningRate(double rate)
          Set the learning rate, this is value is essentially a percent.
 void setMomentum(double m)
          Set the momentum for training.
 double updateWeight(double[] gradients, double[] lastGradient, int index)
          Update a weight.
 
Methods inherited from class org.encog.neural.networks.training.propagation.Propagation
calculateGradients, finishTraining, fixFlatSpot, getBatchSize, getCurrentFlatNetwork, getLastGradient, getMethod, getThreadCount, iteration, iteration, learn, learnLimited, report, rollIteration, setBatchSize, setErrorFunction, setThreadCount
 
Methods inherited from class org.encog.ml.train.BasicTraining
addStrategy, getError, getImplementationType, getIteration, getStrategies, getTraining, isTrainingDone, postIteration, preIteration, setError, setIteration, setTraining
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 
Methods inherited from interface org.encog.ml.train.MLTrain
addStrategy, getError, getImplementationType, getIteration, getStrategies, getTraining, isTrainingDone, setError, setIteration
 

Field Detail

LAST_DELTA

public static final String LAST_DELTA
The resume key for backpropagation.

See Also:
Constant Field Values
Constructor Detail

Backpropagation

public Backpropagation(ContainsFlat network,
                       MLDataSet training)
Create a class to train using backpropagation. Use auto learn rate and momentum. Use the CPU to train.

Parameters:
network - The network that is to be trained.
training - The training data to be used for backpropagation.

Backpropagation

public Backpropagation(ContainsFlat network,
                       MLDataSet training,
                       double theLearnRate,
                       double theMomentum)
Parameters:
network - The network that is to be trained
training - The training set
theLearnRate - The rate at which the weight matrix will be adjusted based on learning.
theMomentum - The influence that previous iteration's training deltas will have on the current iteration.
Method Detail

canContinue

public boolean canContinue()

Specified by:
canContinue in interface MLTrain
Returns:
True if the training can be paused, and later continued.

getLastDelta

public double[] getLastDelta()
Returns:
The last delta values.

getLearningRate

public double getLearningRate()
Specified by:
getLearningRate in interface LearningRate
Returns:
The learning rate, this is value is essentially a percent. It is the degree to which the gradients are applied to the weight matrix to allow learning.

getMomentum

public double getMomentum()
Specified by:
getMomentum in interface Momentum
Returns:
The momentum for training. This is the degree to which changes from which the previous training iteration will affect this training iteration. This can be useful to overcome local minima.

isValidResume

public boolean isValidResume(TrainingContinuation state)
Determine if the specified continuation object is valid to resume with.

Parameters:
state - The continuation object to check.
Returns:
True if the specified continuation object is valid for this training method and network.

pause

public TrainingContinuation pause()
Pause the training.

Specified by:
pause in interface MLTrain
Returns:
A training continuation object to continue with.

resume

public void resume(TrainingContinuation state)
Resume training.

Specified by:
resume in interface MLTrain
Parameters:
state - The training state to return to.

setLearningRate

public void setLearningRate(double rate)
Set the learning rate, this is value is essentially a percent. It is the degree to which the gradients are applied to the weight matrix to allow learning.

Specified by:
setLearningRate in interface LearningRate
Parameters:
rate - The learning rate.

setMomentum

public void setMomentum(double m)
Set the momentum for training. This is the degree to which changes from which the previous training iteration will affect this training iteration. This can be useful to overcome local minima.

Specified by:
setMomentum in interface Momentum
Parameters:
m - The momentum.

updateWeight

public double updateWeight(double[] gradients,
                           double[] lastGradient,
                           int index)
Update a weight.

Specified by:
updateWeight in class Propagation
Parameters:
gradients - The gradients.
lastGradient - The last gradients.
index - The index.
Returns:
The weight delta.

initOthers

public void initOthers()
Perform training method specific init.

Specified by:
initOthers in class Propagation


Copyright © 2014. All Rights Reserved.