org.joone.engine.learning

Class TeacherSynapse

java.lang.Object

org.joone.engine.Synapse

org.joone.engine.learning.AbstractTeacherSynapse

org.joone.engine.learning.TeacherSynapse

All Implemented Interfaces:

java.io.Serializable, InputPatternListener, Learnable, LearnableSynapse, NeuralElement, OutputPatternListener, Inspectable

Direct Known Subclasses:

FahlmanTeacherSynapse

public class TeacherSynapse
extends AbstractTeacherSynapse

Final element of a neural network; it permits to calculate both the error of the last training cycle and the vector containing the error pattern to apply to the net to calculate the backprop algorithm.

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
protected double	GlobalError The error being calculated for the current epoch.
protected static ILogger	log Logger

Fields inherited from class org.joone.engine.learning.AbstractTeacherSynapse

currEpoch, desired, error, lastErrorPatternReady, net

Fields inherited from class org.joone.engine.Synapse

array, b_pattern, bitems, bouts, count, enabled, fwdLock, inps, items, learnable, m_batch, m_pattern, myLearner, outs, revLock

Constructor Summary

Constructors

Constructor and Description
TeacherSynapse()

Method Summary

Methods

Modifier and Type	Method and Description
double	calculateError(double aDesired, double anOutput, int anIndex) Calculates the error to be backpropaged for a single output neuron.
double	calculateGlobalError() This method is called after an epoch finished and the global error should be calculated.
void	fwdPut(Pattern pattern) Method to put a pattern forward to the next layer

Methods inherited from class org.joone.engine.learning.AbstractTeacherSynapse

backward, check, constructErrorPattern, epochFinished, forward, fwdGet, getDesired, getLastErrorPattern, getSeenPatterns, incSeenPatterns, init, isFirstTime, isLastErrorPatternReady, netStoppedError, pushError, readResolve, reset, resetInput, revGet, revPut, setArrays, setDesired, setDimensions, setFirstTime, setInputDimension, setMonitor, setSeenPatterns, stopTheNet

Methods inherited from class org.joone.engine.Synapse

addNoise, canCountSteps, fwdPattern_consume, fwdPattern_produce, getCount, getFwdLock, getIgnoreBefore, getInputDimension, getLearner, getLearningRate, getMomentum, getMonitor, getName, getOutputDimension, getRevLock, getSynapseNameSafely, getWeights, initLearner, InspectableTitle, Inspections, isEnabled, isInputFull, isLoopBack, isOutputFull, randomize, revPattern_consume, revPattern_produce, setEnabled, setIgnoreBefore, setInputFull, setLearningRate, setLoopBack, setMomentum, setName, setOutputDimension, setOutputFull, setWeights, warnLogger, warnLogger

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

log

protected static final ILogger log

Logger

GlobalError

protected transient double GlobalError

The error being calculated for the current epoch.

Constructor Detail

TeacherSynapse

public TeacherSynapse()

Method Detail

calculateError

public double calculateError(double aDesired,
                    double anOutput,
                    int anIndex)

Description copied from class: AbstractTeacherSynapse

Calculates the error to be backpropaged for a single output neuron. (The function should also update the global error internally).

Specified by:

calculateError in class AbstractTeacherSynapse

Parameters:

aDesired - the desired output

anOutput - the actual output of a single neuron

anIndex - the index of the output neuron

Returns:

the error to be back propagated

calculateGlobalError

public double calculateGlobalError()

Description copied from class: AbstractTeacherSynapse

This method is called after an epoch finished and the global error should be calculated.

Specified by:

calculateGlobalError in class AbstractTeacherSynapse

Returns:

the global error (at the end of an epoch).

fwdPut

public void fwdPut(Pattern pattern)

Description copied from interface: OutputPatternListener

Method to put a pattern forward to the next layer

Specified by:

fwdPut in interface OutputPatternListener

Overrides:

fwdPut in class AbstractTeacherSynapse

Parameters:

pattern - neural.engine.Pattern