org.simbrain.network.trainers

Class LMSIterative

java.lang.Object

org.simbrain.network.trainers.Trainer

org.simbrain.network.trainers.IterableTrainer

org.simbrain.network.trainers.LMSIterative

public class LMSIterative
extends IterableTrainer

Train using least mean squares.

Author:

jyoshimi

Nested Class Summary

Nested classes/interfaces inherited from class org.simbrain.network.trainers.IterableTrainer

IterableTrainer.StoppingCondition

Nested classes/interfaces inherited from class org.simbrain.network.trainers.Trainer

Trainer.DataNotInitializedException

Field Summary

Fields inherited from class org.simbrain.network.trainers.Trainer

network

Constructor Summary

Constructors

Constructor and Description
LMSIterative(Trainable network) Construct a least mean squares iterative panel.

Method Summary

Modifier and Type	Method and Description
void	apply() Apply the algorithm.
double	getError() Get the current MSE error.
double	getLearningRate()
void	randomize() A standard way of randomizing networks to which LMSIterative is applied, by randomizing bias on output nodes and the single layer of weights.
void	setLearningRate(double learningRate)

Methods inherited from class org.simbrain.network.trainers.IterableTrainer

addErrorListener, fireErrorUpdated, getErrorListeners, getErrorThreshold, getIteration, getIterationsBeforeStopping, getMinimumNumRows, getStoppingCond, getStoppingCondition, getValidationError, incrementIteration, isUpdateCompleted, iterate, removeErrorListener, setErrorThreshold, setIteration, setIterationsBeforeStopping, setStoppingCond, setStoppingCondition, setUpdateCompleted

Methods inherited from class org.simbrain.network.trainers.Trainer

addListener, fireProgressUpdate, fireTrainingBegin, fireTrainingEnd, getListeners, getTrainable, getTrainableNetwork, removeListener, revalidateSynapseGroups

Methods inherited from class java.lang.Object

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

Constructor Detail

LMSIterative

public LMSIterative(Trainable network)

Construct a least mean squares iterative panel.

Parameters:

network -

Method Detail

getError

public double getError()

Get the current MSE error.

Specified by:

getError in class IterableTrainer

Returns:

the current MSE error

apply

public void apply()

Description copied from class: Trainer

Apply the algorithm.

Specified by:

apply in class Trainer

randomize

public void randomize()

A standard way of randomizing networks to which LMSIterative is applied, by randomizing bias on output nodes and the single layer of weights.

Specified by:

randomize in class IterableTrainer

getLearningRate

public double getLearningRate()

Returns:

the learningRate

setLearningRate

public void setLearningRate(double learningRate)

Parameters:

learningRate - the learningRate to set