org.deeplearning4j.nn.updater

Class MultiLayerUpdater

java.lang.Object

org.deeplearning4j.nn.updater.MultiLayerUpdater

All Implemented Interfaces:

Serializable, Updater

public class MultiLayerUpdater
extends Object
implements Updater

MultiLayerUpdater: Gradient updater for MultiLayerNetworks. Expects backprop gradients for all layers to be in single Gradient object, keyed by "0_b", "1_w" etc., as per MultiLayerNetwork.backward()

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
MultiLayerUpdater(MultiLayerNetwork network)

Method Summary

Modifier and Type	Method and Description
void	update(Layer layer, Gradient gradient, int iteration, int batchSize) Updater: updates the model

Methods inherited from class java.lang.Object

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

Constructor Detail

MultiLayerUpdater

public MultiLayerUpdater(MultiLayerNetwork network)

Method Detail

update

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

Description copied from interface: Updater

Updater: updates the model

Specified by:

update in interface Updater