org.joone.engine.extenders
Class GradientExtender

java.lang.Object
  extended by org.joone.engine.extenders.LearnerExtender
      extended by org.joone.engine.extenders.GradientExtender

public abstract class GradientExtender
extends LearnerExtender

This abstract class describes the methods needed for a gradient extender, that is, a class that computes / changes the gradient value according to some algorithm.

Author:
Boris Jansen

Constructor Summary
GradientExtender()
          Creates a new instance of DeltaExtender
 
Method Summary
abstract  double getGradientBias(double[] currentGradientOuts, int j, double aPreviousGradient)
          Computes the gradient value for a bias.
abstract  double getGradientWeight(double[] currentInps, int j, double[] currentPattern, int k, double aPreviousGradient)
          Computes the gradient value for a weight.
 
Methods inherited from class org.joone.engine.extenders.LearnerExtender
getLearner, isEnabled, postBiasUpdate, postWeightUpdate, preBiasUpdate, preWeightUpdate, setEnabled, setLearner
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

GradientExtender

public GradientExtender()
Creates a new instance of DeltaExtender

Method Detail

getGradientBias

public abstract double getGradientBias(double[] currentGradientOuts,
                                       int j,
                                       double aPreviousGradient)
Computes the gradient value for a bias.

Parameters:
currentGradientOuts - the back propagated gradients.
j - the index of the bias.
aPreviousGradient - a gradient value calculated by a previous gradient extender.

getGradientWeight

public abstract double getGradientWeight(double[] currentInps,
                                         int j,
                                         double[] currentPattern,
                                         int k,
                                         double aPreviousGradient)
Computes the gradient value for a weight.

Parameters:
currentInps - the forwarded input.
j - the input index of the weight.
currentPattern - the back propagated gradients.
k - the output index of the weight.
aPreviousGradient - a gradients value calculated by a previous gradients extender.


Submit Feedback to pmarrone@users.sourceforge.net