net.sourceforge.cilib.neuralnetwork.generic.trainingstrategies
Class FFNN_GD_TrainingStrategy

java.lang.Object
  extended by net.sourceforge.cilib.neuralnetwork.generic.trainingstrategies.FFNN_GD_TrainingStrategy
All Implemented Interfaces:
Initializable, TrainingStrategy, Observer

public class FFNN_GD_TrainingStrategy
extends Object
implements TrainingStrategy, Observer

Author:
stefanv This is an Application in the Generic Framework - it does not form part of the framework. It implements multi layer Gradient Decent (GD) training for Feedforward NN (FFNN). To use the class, call the invokeTrainer() method with the last presented pattern as an argument.

Constructor Summary
FFNN_GD_TrainingStrategy()
           
 
Method Summary
 void initialize()
           
 void invokeTrainer(Object args)
           
 void postEpochActions(Object args)
           
 void preEpochActions(Object args)
           
 void setDelta(ErrorSignal delta)
           
 void setLearningRate(Double learningRate)
           
 void setMomentum(Double momentum)
           
 void setTopology(NeuralNetworkTopology topo)
           
 void updateFanInWeights(NeuronConfig n, Type delta)
           
 void validate()
           
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

FFNN_GD_TrainingStrategy

public FFNN_GD_TrainingStrategy()
Method Detail

initialize

public void initialize()
Specified by:
initialize in interface Initializable

updateFanInWeights

public void updateFanInWeights(NeuronConfig n,
                               Type delta)

invokeTrainer

public void invokeTrainer(Object args)
Specified by:
invokeTrainer in interface TrainingStrategy

validate

public void validate()
Specified by:
validate in interface Observer

preEpochActions

public void preEpochActions(Object args)
Specified by:
preEpochActions in interface TrainingStrategy

postEpochActions

public void postEpochActions(Object args)
Specified by:
postEpochActions in interface TrainingStrategy

setDelta

public void setDelta(ErrorSignal delta)

setLearningRate

public void setLearningRate(Double learningRate)

setMomentum

public void setMomentum(Double momentum)

setTopology

public void setTopology(NeuralNetworkTopology topo)
Specified by:
setTopology in interface TrainingStrategy


Copyright © 2009 CIRG. All Rights Reserved.