org.deeplearning4j.nn.conf.weightnoise

Class WeightNoise

java.lang.Object

org.deeplearning4j.nn.conf.weightnoise.WeightNoise

All Implemented Interfaces:

Serializable, Cloneable, IWeightNoise

public class WeightNoise
extends Object
implements IWeightNoise

Apply noise of the specified distribution to the weights at training time. Note that both additive and multiplicative modes are supported - when additive, noise should be mean 0, when multiplicative, noise should be mean 1. That is, additive noise: x = x + noise
multiplicative noise: x = x * noise

Author:

Alex Black

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
WeightNoise(Distribution distribution)
WeightNoise(Distribution distribution, boolean additive)
WeightNoise(Distribution distribution, boolean applyToBias, boolean additive)

Method Summary

Modifier and Type	Method and Description
WeightNoise	clone()
INDArray	getParameter(Layer layer, String paramKey, int iteration, int epoch, boolean train, LayerWorkspaceMgr workspaceMgr) Get the parameter, after applying weight noise

Methods inherited from class java.lang.Object

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

Constructor Detail

WeightNoise

public WeightNoise(Distribution distribution)

Parameters:

distribution - Distribution for additive noise

WeightNoise

public WeightNoise(Distribution distribution,
                   boolean additive)

Parameters:

distribution - Distribution for noise

additive - If true: noise is added to weights. If false: noise is multiplied by weights

WeightNoise

public WeightNoise(Distribution distribution,
                   boolean applyToBias,
                   boolean additive)

Parameters:

distribution - Distribution for noise

applyToBias - If true: apply to biases also. If false (default): apply only to weights

additive - If true: noise is added to weights. If false: noise is multiplied by weights

Method Detail

getParameter

public INDArray getParameter(Layer layer,
                             String paramKey,
                             int iteration,
                             int epoch,
                             boolean train,
                             LayerWorkspaceMgr workspaceMgr)

Description copied from interface: IWeightNoise

Get the parameter, after applying weight noise

Specified by:

getParameter in interface IWeightNoise

Parameters:

layer - Layer to get the parameter for

paramKey - Parameter key

iteration - Iteration number

epoch - Epoch number

train - If true: training. False: at test time

Returns:

Parameter, after applying weight noise

clone

public WeightNoise clone()

Specified by:

clone in interface IWeightNoise

Overrides:

clone in class Object