Implementation of the concat performance class. More...

#include <concat_performance.hpp>

Public Member Functions
	ConcatPerformance (const size_t inSize=0, OutputLayerType &&outputLayer=OutputLayerType())
	Create the ConcatPerformance object. More...

template<typename eT >
double	Forward (const arma::Mat< eT > &input, arma::Mat< eT > &target)

template<typename eT >
void	Backward (const arma::Mat< eT > &input, const arma::Mat< eT > &target, arma::Mat< eT > &output)
	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	InSize () const
	Get the number of inputs.

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

Detailed Description

template<typename OutputLayerType = NegativeLogLikelihood<>, typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
class mlpack::ann::ConcatPerformance< OutputLayerType, InputDataType, OutputDataType >

Implementation of the concat performance class.

The class works as a feed-forward fully connected network container which plugs performance layers together.

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

◆ ConcatPerformance()

template<typename OutputLayerType , typename InputDataType , typename OutputDataType >

mlpack::ann::ConcatPerformance< OutputLayerType, InputDataType, OutputDataType >::ConcatPerformance	(	const size_t	inSize = `0`,
		OutputLayerType &&	outputLayer = `OutputLayerType()`
	)

Create the ConcatPerformance object.

Parameters

inSize	The number of inputs.
outputLayer	Output layer used to evaluate the network.

Member Function Documentation

◆ Backward()

template<typename OutputLayerType , typename InputDataType , typename OutputDataType >

template<typename eT >

void mlpack::ann::ConcatPerformance< OutputLayerType, InputDataType, OutputDataType >::Backward	(	const arma::Mat< eT > &	input,
		const arma::Mat< eT > &	target,
		arma::Mat< eT > &	output
	)

Ordinary feed backward pass of a neural network.

The negative log likelihood layer expectes that the input contains log-probabilities for each class. The layer also expects a class index, in the range between 1 and the number of classes, as target when calling the Forward function.