net.sourceforge.jabm.learning
Class SlidingWindowLearner

java.lang.Object
  net.sourceforge.jabm.learning.AbstractLearner
      net.sourceforge.jabm.learning.SlidingWindowLearner

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, ContinuousLearner, Learner, MimicryLearner, SelfKnowledgable, Prototypeable

public class SlidingWindowLearner
extends AbstractLearner
implements MimicryLearner, SelfKnowledgable, Prototypeable, java.io.Serializable

maintains a sliding window over the trained data series and use the average of data items falling into the window as the output learned.

See Also:

Serialized Form

Field Summary

protected double	currentOutput The current output level.
protected FixedLengthQueue	memory
static java.lang.String	P_DEF_BASE
static java.lang.String	P_WINDOWSIZE
protected cern.jet.random.AbstractContinousDistribution	randomParamDistribution
protected int	windowSize A parameter used to adjust the size of the window

Fields inherited from class net.sourceforge.jabm.learning.AbstractLearner

monitor

Constructor Summary

SlidingWindowLearner(cern.jet.random.AbstractContinousDistribution randomParamDistribution)

SlidingWindowLearner(cern.jet.random.engine.RandomEngine prng)

Method Summary

double	act() Generate an output from the learning algorithm.
protected void	createMemory()
void	dumpState(DataWriter out) Write out our state data to the specified data writer.
double	getCurrentOutput()
double	getLearningDelta() Return a value indicative of the amount of learning that occured during the last iteration.
int	getWindowSize()
boolean	goodEnough()
void	initialise()
java.lang.Object	protoClone()
void	randomInitialise() Initialise with random values for free parameters
void	reset()
void	setOutputLevel(double currentOutput) no effect on FixedLengthQueue-based next output!
void	setWindowSize(int windowSize)
java.lang.String	toString()
void	train(double target) Provide a training signal to the learning algorithm.

Methods inherited from class net.sourceforge.jabm.learning.AbstractLearner

monitor

Methods inherited from class java.lang.Object

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

Methods inherited from interface net.sourceforge.jabm.learning.Learner

monitor

Field Detail

randomParamDistribution

protected cern.jet.random.AbstractContinousDistribution randomParamDistribution

windowSize

protected int windowSize

A parameter used to adjust the size of the window

P_WINDOWSIZE

public static final java.lang.String P_WINDOWSIZE

See Also:

Constant Field Values

currentOutput

protected double currentOutput

The current output level.

P_DEF_BASE

public static final java.lang.String P_DEF_BASE

See Also:

Constant Field Values

memory

protected FixedLengthQueue memory

Constructor Detail

SlidingWindowLearner

public SlidingWindowLearner(cern.jet.random.engine.RandomEngine prng)

SlidingWindowLearner

public SlidingWindowLearner(cern.jet.random.AbstractContinousDistribution randomParamDistribution)

Method Detail

initialise

public void initialise()

reset

public void reset()

randomInitialise

public void randomInitialise()

Description copied from interface: MimicryLearner

Initialise with random values for free parameters

Specified by:

randomInitialise in interface MimicryLearner

setWindowSize

public void setWindowSize(int windowSize)

getWindowSize

public int getWindowSize()

createMemory

protected void createMemory()

act

public double act()

Description copied from interface: ContinuousLearner

Generate an output from the learning algorithm.

Specified by:

act in interface ContinuousLearner

train

public void train(double target)

Description copied from interface: MimicryLearner

Provide a training signal to the learning algorithm.

Specified by:

train in interface MimicryLearner

dumpState

public void dumpState(DataWriter out)

Description copied from interface: Learner

Write out our state data to the specified data writer.

Specified by:

dumpState in interface Learner

Specified by:

dumpState in class AbstractLearner

getCurrentOutput

public double getCurrentOutput()

setOutputLevel

public void setOutputLevel(double currentOutput)

no effect on FixedLengthQueue-based next output!

Specified by:

setOutputLevel in interface MimicryLearner

getLearningDelta

public double getLearningDelta()

Description copied from interface: Learner

Return a value indicative of the amount of learning that occured during the last iteration. Values close to 0.0 indicate that the learner has converged to an equilibrium state.

Specified by:

getLearningDelta in interface Learner

Specified by:

getLearningDelta in class AbstractLearner

Returns:

A double representing the amount of learning that occured.

protoClone

public java.lang.Object protoClone()

Specified by:

protoClone in interface Prototypeable

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

goodEnough

public boolean goodEnough()

Specified by:

goodEnough in interface SelfKnowledgable