org.deeplearning4j.nn.gradient

Class MultiLayerGradient

java.lang.Object

org.deeplearning4j.nn.gradient.MultiLayerGradient

All Implemented Interfaces:

Serializable, Persistable

public class MultiLayerGradient
extends Object
implements Persistable

Gradient for a whole multi layer network

Author:

Adam Gibson

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
MultiLayerGradient(List<NeuralNetworkGradient> gradients, LogisticRegressionGradient logRegGradient)

Method Summary

Methods

Modifier and Type	Method and Description
void	div(int num)
List<NeuralNetworkGradient>	getGradients()
LogisticRegressionGradient	getLogRegGradient()
void	load(InputStream is)
void	setGradients(List<NeuralNetworkGradient> gradients)
void	setLogRegGradient(LogisticRegressionGradient logRegGradient)
void	write(OutputStream os)

Methods inherited from class java.lang.Object

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

Constructor Detail

MultiLayerGradient

public MultiLayerGradient(List<NeuralNetworkGradient> gradients,
                  LogisticRegressionGradient logRegGradient)

Method Detail

write

public void write(OutputStream os)

Specified by:

write in interface Persistable

load

public void load(InputStream is)

Specified by:

load in interface Persistable

div

public void div(int num)

getGradients

public List<NeuralNetworkGradient> getGradients()

setGradients

public void setGradients(List<NeuralNetworkGradient> gradients)

getLogRegGradient

public LogisticRegressionGradient getLogRegGradient()

setLogRegGradient

public void setLogRegGradient(LogisticRegressionGradient logRegGradient)