The select module selects the specified column from a given input matrix. More...

#include <select.hpp>

Public Member Functions
	Select (const size_t index=0, const size_t elements=0)
	Create the Select object. More...

template<typename eT >
void	Forward (const arma::Mat< eT > &input, arma::Mat< eT > &output)
	Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...

template<typename eT >
void	Backward (const arma::Mat< eT > &, const arma::Mat< eT > &gy, arma::Mat< eT > &g)
	Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards trough f. 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 const &	Index () const
	Get the column index.

size_t const &	NumElements () const
	Get the number of elements selected.

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

Detailed Description

The select module selects the specified column from a given input matrix.

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::Select< InputDataType, OutputDataType >::Select	(	const size_t	index = `0`,
		const size_t	elements = `0`
	)

Create the Select object.

Parameters

index	The column which should be extracted from the given input.
elements	The number of elements that should be used.

template<typename InputDataType , typename OutputDataType >

template<typename eT >

void mlpack::ann::Select< InputDataType, OutputDataType >::Backward	(	const arma::Mat< eT > &	,
		const arma::Mat< eT > &	gy,
		arma::Mat< eT > &	g
	)

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

Using the results from the feed forward pass.

Parameters

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

template<typename InputDataType , typename OutputDataType >

template<typename eT >

void mlpack::ann::Select< InputDataType, OutputDataType >::Forward	(	const arma::Mat< eT > &	input,
		arma::Mat< eT > &	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.

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