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

See Also:

Serialized Form

Constructor Summary

Constructors

Modifier	Constructor and Description
	GaussianNoise(double stddev)
protected	GaussianNoise(double stddev, ISchedule stddevSchedule)
	GaussianNoise(ISchedule stddevSchedule)

Method Summary

Modifier and Type	Method and Description
INDArray	applyDropout(INDArray inputActivations, INDArray output, int iteration, int epoch, LayerWorkspaceMgr workspaceMgr)
INDArray	backprop(INDArray gradAtOutput, INDArray gradAtInput, int iteration, int epoch) Perform backprop.
void	clear() Clear the internal state (for example, dropout mask) if any is present
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(ISchedule stddevSchedule)

Parameters:

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

GaussianNoise

protected GaussianNoise(double stddev,
                        ISchedule stddevSchedule)

Method Detail

applyDropout

public INDArray applyDropout(INDArray inputActivations,
                             INDArray output,
                             int iteration,
                             int epoch,
                             LayerWorkspaceMgr workspaceMgr)

Specified by:

applyDropout in interface IDropout

Parameters:

inputActivations - Input activations array

output - The result array (same as inputArray for in-place ops) for the post-dropout activations

iteration - Current iteration number

epoch - Current epoch number

workspaceMgr - Workspace manager, if any storage is required (use ArrayType.INPUT)

Returns:

The output (resultArray) after applying dropout

backprop

public INDArray backprop(INDArray gradAtOutput,
                         INDArray gradAtInput,
                         int iteration,
                         int epoch)

Description copied from interface: IDropout

Perform backprop. This should also clear the internal state (dropout mask) if any is present

Specified by:

backprop in interface IDropout

Parameters:

gradAtOutput - Gradients at the output of the dropout op - i.e., dL/dOut

gradAtInput - Gradients at the input of the dropout op - i.e., dL/dIn. Use the same array as gradAtOutput to apply the backprop gradient in-place

iteration - Current iteration

epoch - Current epoch

Returns:

Same array as gradAtInput - i.e., gradient after backpropagating through dropout op - i.e., dL/dIn

clear

public void clear()

Description copied from interface: IDropout

Clear the internal state (for example, dropout mask) if any is present

Specified by:

clear in interface IDropout

clone

public IDropout clone()

Specified by:

clone in interface IDropout

Overrides:

clone in class Object