Implementation of the constant layer. More...

#include <constant.hpp>

Public Member Functions
	Constant (const size_t outSize=0, const double scalar=0.0)
	Create the Constant object that outputs a given constant scalar value given any input value. More...

template<typename InputType , typename OutputType >
void	Forward (const InputType &input, OutputType &output)
	Ordinary feed forward pass of a neural network. More...

template<typename DataType >
void	Backward (const DataType &, const DataType &, DataType &g)
	Ordinary feed backward pass of a neural network. More...

OutputDataType &	OutputParameter () const
	Get the output parameter.

OutputDataType &	OutputParameter ()
	Modify the output parameter.

OutputDataType &	Delta () const
	Get the delta.

OutputDataType &	Delta ()
	Modify the delta.

size_t	OutSize () const
	Get the output size.

size_t	WeightSize () const
	Get the size of the weights.

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

Detailed Description

Implementation of the constant layer.

The constant layer outputs a given constant value given any input value.

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).

Constructor & Destructor Documentation

template<typename InputDataType , typename OutputDataType >

mlpack::ann::Constant< InputDataType, OutputDataType >::Constant	(	const size_t	outSize = `0`,
		const double	scalar = `0.0`
	)

Create the Constant object that outputs a given constant scalar value given any input value.

Parameters

outSize	The number of output units.
scalar	The constant value used to create the constant output.

template<typename InputDataType , typename OutputDataType >

template<typename DataType >

void mlpack::ann::Constant< InputDataType, OutputDataType >::Backward	(	const DataType &	,
		const DataType &	,
		DataType &	g
	)

Ordinary feed backward pass of a neural network.

The backward pass of the constant layer is returns always a zero output error matrix.

Parameters

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

template<typename InputDataType , typename OutputDataType >

template<typename InputType , typename OutputType >

void mlpack::ann::Constant< InputDataType, OutputDataType >::Forward	(	const InputType &	input,
		OutputType &	output
	)

Ordinary feed forward pass of a neural network.

The forward pass fills the output with the specified constant parameter.

Parameters

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

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