org.deeplearning4j.nn.updater

Class BaseUpdater

java.lang.Object

org.deeplearning4j.nn.updater.BaseUpdater

All Implemented Interfaces:

Serializable, Updater

Direct Known Subclasses:

AdaDeltaUpdater, AdaGradUpdater, AdamUpdater, NesterovsUpdater, NoOpUpdater, RmsPropUpdater, SgdUpdater

public abstract class BaseUpdater
extends Object
implements Updater

Author:

Adam Gibson

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
protected Map<String,org.nd4j.linalg.learning.GradientUpdater>	updaterForVariable

Constructor Summary

Constructors

Constructor and Description
BaseUpdater()

Method Summary

Modifier and Type	Method and Description
abstract void	init()
abstract org.nd4j.linalg.learning.GradientUpdater	init(String variable, org.nd4j.linalg.api.ndarray.INDArray gradient, Layer layer)
void	postApply(Layer layer, org.nd4j.linalg.api.ndarray.INDArray gradient, String param) Apply the regularization
void	update(Layer layer, Gradient gradient, int iteration) Updater: updates the model

Methods inherited from class java.lang.Object

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

Field Detail

updaterForVariable

protected Map<String,org.nd4j.linalg.learning.GradientUpdater> updaterForVariable

Constructor Detail

BaseUpdater

public BaseUpdater()

Method Detail

update

public void update(Layer layer,
                   Gradient gradient,
                   int iteration)

Description copied from interface: Updater

Updater: updates the model

Specified by:

update in interface Updater

postApply

public void postApply(Layer layer,
                      org.nd4j.linalg.api.ndarray.INDArray gradient,
                      String param)

Apply the regularization

Parameters:

layer -

gradient -

param -

init

public abstract void init()

init

public abstract org.nd4j.linalg.learning.GradientUpdater init(String variable,
                                                              org.nd4j.linalg.api.ndarray.INDArray gradient,
                                                              Layer layer)