LeakyReLUType< MatType > Class Template Reference

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

Inheritance diagram for LeakyReLUType< MatType >:

Public Member Functions

 LeakyReLUType (const double alpha=0.03)
 Create the LeakyReLU object using the specified parameters. More...

 
 LeakyReLUType (const LeakyReLUType &other)
 Copy the given LeakyReLUType. More...

 
 LeakyReLUType (LeakyReLUType &&other)
 Take ownership of the given LeakyReLUType. More...

 
virtual ~LeakyReLUType ()
 
double const & Alpha () const
 Get the non zero gradient. More...

 
double & Alpha ()
 Modify the non zero gradient. More...

 
void Backward (const MatType &input, const MatType &gy, MatType &g)
 Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f. More...

 
LeakyReLUTypeClone () const
 Clone the LeakyReLUType object. This handles polymorphism correctly. More...

 
void Forward (const MatType &input, MatType &output)
 Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...

 
LeakyReLUTypeoperator= (const LeakyReLUType &other)
 Copy the given LeakyReLUType. More...

 
LeakyReLUTypeoperator= (LeakyReLUType &&other)
 Take ownership of the given LeakyReLUType. More...

 
template
<
typename
Archive
>
void serialize (Archive &ar, const uint32_t)
 Serialize the layer. More...

 
- Public Member Functions inherited from Layer< MatType >
 Layer ()
 Default constructor. More...

 
 Layer (const Layer &layer)
 Copy constructor. This is not responsible for copying weights! More...

 
 Layer (Layer &&layer)
 Move constructor. This is not responsible for moving weights! More...

 
virtual ~Layer ()
 Default deconstructor. More...

 
virtual void ComputeOutputDimensions ()
 Compute the output dimensions. More...

 
virtual void CustomInitialize (MatType &, const size_t)
 Override the weight matrix of the layer. More...

 
virtual void Forward (const MatType &, const MatType &)
 Takes an input and output object, and computes the corresponding loss of the layer. More...

 
virtual void Gradient (const MatType &, const MatType &, MatType &)
 Computing the gradient of the layer with respect to its own input. More...

 
const std::vector< size_t > & InputDimensions () const
 Get the input dimensions. More...

 
std::vector< size_t > & InputDimensions ()
 Modify the input dimensions. More...

 
virtual double Loss ()
 Get the layer loss. More...

 
virtual Layeroperator= (const Layer &layer)
 Copy assignment operator. This is not responsible for copying weights! More...

 
virtual Layeroperator= (Layer &&layer)
 Move assignment operator. This is not responsible for moving weights! More...

 
const std::vector< size_t > & OutputDimensions ()
 Get the output dimensions. More...

 
virtual size_t OutputSize () final
 Get the number of elements in the output from this layer. More...

 
virtual const MatType & Parameters () const
 Get the parameters. More...

 
virtual MatType & Parameters ()
 Set the parameters. More...

 
template
<
typename
Archive
>
void serialize (Archive &ar, const uint32_t)
 Serialize the layer. More...

 
virtual void SetWeights (typename MatType::elem_type *)
 Reset the layer parameter. More...

 
virtual bool const & Training () const
 Get whether the layer is currently in training mode. More...

 
virtual bool & Training ()
 Modify whether the layer is currently in training mode. More...

 
virtual size_t WeightSize () const
 Get the total number of trainable weights in the layer. More...

 

Additional Inherited Members

- Protected Attributes inherited from Layer< MatType >
std::vector< size_t > inputDimensions
 Logical input dimensions of each point. More...

 
std::vector< size_t > outputDimensions
 Logical output dimensions of each point. More...

 
bool training
 If true, the layer is in training mode; otherwise, it is in testing mode. More...

 
bool validOutputDimensions
 This is true if ComputeOutputDimensions() has been called, and outputDimensions can be considered to be up-to-date. More...

 

Detailed Description


template
<
typename
MatType
=
arma::mat
>

class mlpack::ann::LeakyReLUType< MatType >

The LeakyReLU activation function, defined by.

\begin{eqnarray*} f(x) &=& \max(x, alpha*x) \\ f'(x) &=& \left\{ \begin{array}{lr} 1 & : x > 0 \\ alpha & : x \le 0 \end{array} \right. \end{eqnarray*}

Template Parameters
MatTypeMatrix representation to accept as input and use for computation.

Definition at line 41 of file leaky_relu.hpp.

Constructor & Destructor Documentation

◆ LeakyReLUType() [1/3]

LeakyReLUType ( const double  alpha = 0.03)

Create the LeakyReLU object using the specified parameters.

The non zero gradient can be adjusted by specifying the parameter alpha in the range 0 to 1. Default (alpha = 0.03)

Parameters
alphaNon zero gradient.

Referenced by LeakyReLUType< MatType >::Clone(), and LeakyReLUType< MatType >::~LeakyReLUType().

◆ ~LeakyReLUType()

◆ LeakyReLUType() [2/3]

LeakyReLUType ( const LeakyReLUType< MatType > &  other)

Copy the given LeakyReLUType.

◆ LeakyReLUType() [3/3]

LeakyReLUType ( LeakyReLUType< MatType > &&  other)

Take ownership of the given LeakyReLUType.

Member Function Documentation

◆ Alpha() [1/2]

double const& Alpha ( ) const
inline

Get the non zero gradient.

Definition at line 89 of file leaky_relu.hpp.

◆ Alpha() [2/2]

double& Alpha ( )
inline

Modify the non zero gradient.

Definition at line 91 of file leaky_relu.hpp.

References LeakyReLUType< MatType >::serialize().

◆ Backward()

void Backward ( const MatType &  input,
const MatType &  gy,
MatType &  g 
)
virtual

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.
gyThe backpropagated error.
gThe calculated gradient.

Reimplemented from Layer< MatType >.

Referenced by LeakyReLUType< MatType >::~LeakyReLUType().

◆ Clone()

LeakyReLUType* Clone ( ) const
inlinevirtual

Clone the LeakyReLUType object. This handles polymorphism correctly.

Implements Layer< MatType >.

Definition at line 54 of file leaky_relu.hpp.

References LeakyReLUType< MatType >::LeakyReLUType().

◆ Forward()

void Forward ( const MatType &  input,
MatType &  output 
)
virtual

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 specified function.
outputResulting output activation.

Reimplemented from Layer< MatType >.

Referenced by LeakyReLUType< MatType >::~LeakyReLUType().

◆ operator=() [1/2]

LeakyReLUType& operator= ( const LeakyReLUType< MatType > &  other)

◆ operator=() [2/2]

LeakyReLUType& operator= ( LeakyReLUType< MatType > &&  other)

Take ownership of the given LeakyReLUType.

◆ serialize()

void serialize ( Archive &  ar,
const uint32_t   
)

Serialize the layer.

Referenced by LeakyReLUType< MatType >::Alpha().


The documentation for this class was generated from the following file:
  • /home/jenkins-mlpack/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/layer/leaky_relu.hpp