ELU< InputDataType, OutputDataType > Class Template Reference

The ELU activation function, defined by. More...

Public Member Functions
	ELU ()
	Create the ELU object. More...
	ELU (const double alpha)
	Create the ELU object using the specified parameter. More...
double const &	Alpha () const
	Get the non zero gradient. More...
double &	Alpha ()
	Modify the non zero gradient. More...
template < typename DataType >
void	Backward (const DataType &input, const 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 const &	Delta () const
	Get the delta. More...
OutputDataType &	Delta ()
	Modify the delta. More...
bool	Deterministic () const
	Get the value of deterministic parameter. More...
bool &	Deterministic ()
	Modify the value of deterministic parameter. 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 const &	Lambda () const
	Get the lambda parameter. More...
OutputDataType const &	OutputParameter () const
	Get the output parameter. More...
OutputDataType &	OutputParameter ()
	Modify the output parameter. More...
template < typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer. More...

Detailed Description

template

<

typename

InputDataType

=

arma::mat

,

typename

OutputDataType

=

arma::mat

>

class mlpack::ann::ELU< InputDataType, OutputDataType >

The ELU activation function, defined by.

For more information, read the following paper:

@article{Clevert2015,
  author  = {Djork{-}Arn{\'{e}} Clevert and Thomas Unterthiner and
             Sepp Hochreiter},
  title   = {Fast and Accurate Deep Network Learning by Exponential Linear
             Units (ELUs)},
  journal = {CoRR},
  year    = {2015},
  url     = {https://arxiv.org/abs/1511.07289}
}

The SELU activation function is defined by

For more information, read the following paper:

@article{Klambauer2017,
  author  = {Gunter Klambauer and Thomas Unterthiner and
             Andreas Mayr},
  title   = {Self-Normalizing Neural Networks},
  journal = {Advances in Neural Information Processing Systems},
  year    = {2017},
  url = {https://arxiv.org/abs/1706.02515}
}

In the deterministic mode, there is no computation of the derivative.

Note

During training deterministic should be set to false and during testing/inference deterministic should be set to true.

Make sure to use SELU activation function with normalized inputs and weights initialized with Lecun Normal Initialization.

Template Parameters

InputDataType	Type of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
OutputDataType	Type of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).

Definition at line 111 of file elu.hpp.

Constructor & Destructor Documentation

ELU() [1/2]

ELU

(

)

Create the ELU object.

NOTE: Use this constructor for SELU activation function.

ELU() [2/2]

ELU

(

const double

alpha

)

Create the ELU object using the specified parameter.

The non zero gradient for negative inputs can be adjusted by specifying the ELU hyperparameter alpha (alpha > 0).

Note

Use this constructor for ELU activation function.

Parameters

alpha

Scale parameter for the negative factor.

Member Function Documentation

Alpha() [1/2]

double const& Alpha ( ) const

inline

Get the non zero gradient.

Definition at line 164 of file elu.hpp.

Alpha() [2/2]

double& Alpha ( )

inline

Modify the non zero gradient.

Definition at line 166 of file elu.hpp.

Backward()

void Backward	(	const DataType &	input,
		const 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

input	The propagated input activation f(x).
gy	The backpropagated error.
g	The calculated gradient.

Delta() [1/2]

OutputDataType const& Delta ( ) const

inline

Get the delta.

Definition at line 159 of file elu.hpp.

Delta() [2/2]

OutputDataType& Delta ( )

inline

Modify the delta.

Definition at line 161 of file elu.hpp.

Deterministic() [1/2]

bool Deterministic ( ) const

inline

Get the value of deterministic parameter.

Definition at line 169 of file elu.hpp.

Deterministic() [2/2]

bool& Deterministic ( )

inline

Modify the value of deterministic parameter.

Definition at line 171 of file elu.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

input	Input data used for evaluating the specified function.
output	Resulting output activation.

Lambda()

double const& Lambda ( ) const

inline

Get the lambda parameter.

Definition at line 174 of file elu.hpp.

References ELU< InputDataType, OutputDataType >::serialize().

OutputParameter() [1/2]

OutputDataType const& OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 154 of file elu.hpp.

OutputParameter() [2/2]

OutputDataType& OutputParameter ( )

inline

Modify the output parameter.

Definition at line 156 of file elu.hpp.

serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

Serialize the layer.

Referenced by ELU< InputDataType, OutputDataType >::Lambda().

---

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

• /home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/layer/elu.hpp