org.joone.engine.extenders

Class DeltaRuleExtender

java.lang.Object

org.joone.engine.extenders.LearnerExtender

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.

Constructor Summary

Constructors

Constructor and Description
DeltaRuleExtender() Creates a new instance of DeltaExtender

Method Summary

Modifier and Type	Method and Description
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

isEnabled, postBiasUpdate, postWeightUpdate, preBiasUpdate, preWeightUpdate, setEnabled, setLearner

Methods inherited from class java.lang.Object

equals, 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.