org.joone.engine.extenders
Class DeltaRuleExtender

java.lang.Object
  extended by org.joone.engine.extenders.LearnerExtender
      extended by org.joone.engine.extenders.DeltaRuleExtender
Direct Known Subclasses:
MomentumExtender, RpropExtender, SimulatedAnnealingExtender, WeightDecayExtender

public abstract class DeltaRuleExtender
extends LearnerExtender

This abstract class describes the methods needed for a delta rule extender, that is, a class that computes / changes the delta (update weight) value according to some algorithm.

Author:
Boris Jansen

Constructor Summary
DeltaRuleExtender()
          Creates a new instance of DeltaExtender
 
Method Summary
abstract  double getDelta(double[] currentGradientOuts, int j, double aPreviousDelta)
          Computes the delta value for a bias.
abstract  double getDelta(double[] currentInps, int j, double[] currentPattern, int k, double aPreviousDelta)
          Computes the delta 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

DeltaRuleExtender

public DeltaRuleExtender()
Creates a new instance of DeltaExtender

Method Detail

getDelta

public abstract double getDelta(double[] currentGradientOuts,
                                int j,
                                double aPreviousDelta)
Computes the delta value for a bias.

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

getDelta

public abstract double getDelta(double[] currentInps,
                                int j,
                                double[] currentPattern,
                                int k,
                                double aPreviousDelta)
Computes the delta 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.
aPreviousDelta - a delta value calculated by a previous delta extender.


Submit Feedback to pmarrone@users.sourceforge.net