org.deeplearning4j.nn.conf.dropout

Class GaussianNoise

java.lang.Object

org.deeplearning4j.nn.conf.dropout.GaussianNoise

All Implemented Interfaces:

Serializable, Cloneable, IDropout

public class GaussianNoise
extends Object
implements IDropout

Applies additive, mean-zero Gaussian noise to the input - i.e., x = x + N(0,stddev).
Note that this differs from GaussianDropout, which applies multiplicative mean-1 N(1,s) noise.
Note also that schedules for the standard deviation value can also be used.

Author:

Alex Black

See Also:

Serialized Form

Constructor Summary

Constructors

Modifier	Constructor and Description
	GaussianNoise(double stddev)
protected	GaussianNoise(double stddev, org.nd4j.linalg.schedule.ISchedule stddevSchedule)
	GaussianNoise(org.nd4j.linalg.schedule.ISchedule stddevSchedule)

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	applyDropout(org.nd4j.linalg.api.ndarray.INDArray inputActivations, int iteration, int epoch, boolean inPlace)
IDropout	clone()

Methods inherited from class java.lang.Object

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

Constructor Detail

GaussianNoise

public GaussianNoise(double stddev)

Parameters:

stddev - Standard deviation for the mean 0 Gaussian noise

GaussianNoise

public GaussianNoise(org.nd4j.linalg.schedule.ISchedule stddevSchedule)

Parameters:

stddevSchedule - Schedule for standard deviation for the mean 0 Gaussian noise

GaussianNoise

protected GaussianNoise(double stddev,
                        org.nd4j.linalg.schedule.ISchedule stddevSchedule)

Method Detail

applyDropout

public org.nd4j.linalg.api.ndarray.INDArray applyDropout(org.nd4j.linalg.api.ndarray.INDArray inputActivations,
                                                         int iteration,
                                                         int epoch,
                                                         boolean inPlace)

Specified by:

applyDropout in interface IDropout

Parameters:

inputActivations - Input activations array

iteration - Current iteration number

epoch - Current epoch number

inPlace - If true: modify the input activations in-place. False: Copy the input activations and apply dropout on the copy instead

Returns:

clone

public IDropout clone()

Specified by:

clone in interface IDropout

Overrides:

clone in class Object