mlpack 3.4.2
Public Member Functions | List of all members
SoftShrink< InputDataType, OutputDataType > Class Template Reference

Soft Shrink operator is defined as,. More...

#include <softshrink.hpp>

Public Member Functions

 SoftShrink (const double lambda=0.5)
 Create Soft Shrink object using specified hyperparameter lambda. More...
 
template<typename DataType >
void Backward (const DataType &input, DataType &gy, DataType &g)
 Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f. More...
 
OutputDataType & Delta ()
 Modify the delta. More...
 
OutputDataType const & Delta () const
 Get the delta. More...
 
template<typename InputType , typename OutputType >
void Forward (const InputType &input, OutputType &output)
 Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...
 
double & Lambda ()
 Modify the hyperparameter lambda. More...
 
double const & Lambda () const
 Get the hyperparameter lambda. More...
 
OutputDataType & OutputParameter ()
 Modify the output parameter. More...
 
OutputDataType const & OutputParameter () const
 Get the output parameter. More...
 
template<typename Archive >
void serialize (Archive &ar, const unsigned int)
 Serialize the layer. More...
 

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
class mlpack::ann::SoftShrink< InputDataType, OutputDataType >

Soft Shrink operator is defined as,.

\begin{eqnarray*} f(x) &=& \begin{cases} x - \lambda & : x > \lambda \\ x + \lambda & : x < -\lambda \\ 0 & : otherwise. \\ \end{cases} \\ f'(x) &=& \begin{cases} 1 & : x > \lambda \\ 1 & : x < -\lambda \\ 0 & : otherwise. \end{cases} \end{eqnarray*}

Template Parameters
InputDataTypeType of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
OutputDataTypeType of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).

Definition at line 50 of file softshrink.hpp.

Constructor & Destructor Documentation

◆ SoftShrink()

SoftShrink ( const double  lambda = 0.5)

Create Soft Shrink object using specified hyperparameter lambda.

Parameters
lambdaThe noise level of an image depends on settings of an imaging device. The settings can be used to select appropriate parameters for denoising methods. It is proportional to the noise level entered by the user. And it is calculated by multiplying the noise level sigma of the input(noisy image) and a coefficient 'a' which is one of the training parameters. Default value of lambda is 0.5.

Member Function Documentation

◆ Backward()

void Backward ( const DataType &  input,
DataType &  gy,
DataType &  g 
)

Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f.

Using the results from the feed forward pass.

Parameters
inputThe propagated input activation f(x).
gyThe backpropagated error.
gThe calculated gradient

◆ Delta() [1/2]

OutputDataType & Delta ( )
inline

Modify the delta.

Definition at line 99 of file softshrink.hpp.

◆ Delta() [2/2]

OutputDataType const & Delta ( ) const
inline

Get the delta.

Definition at line 97 of file softshrink.hpp.

◆ Forward()

void Forward ( const InputType &  input,
OutputType &  output 
)

Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f.

Parameters
inputInput data used for evaluating the Soft Shrink function.
outputResulting output activation

◆ Lambda() [1/2]

double & Lambda ( )
inline

Modify the hyperparameter lambda.

Definition at line 104 of file softshrink.hpp.

◆ Lambda() [2/2]

double const & Lambda ( ) const
inline

Get the hyperparameter lambda.

Definition at line 102 of file softshrink.hpp.

◆ OutputParameter() [1/2]

OutputDataType & OutputParameter ( )
inline

Modify the output parameter.

Definition at line 94 of file softshrink.hpp.

◆ OutputParameter() [2/2]

OutputDataType const & OutputParameter ( ) const
inline

Get the output parameter.

Definition at line 92 of file softshrink.hpp.

◆ serialize()

void serialize ( Archive &  ar,
const unsigned int   
)

Serialize the layer.


The documentation for this class was generated from the following file: