mlpack::ann::ReconstructionLoss< InputDataType, OutputDataType, DistType > Class Template Reference

The reconstruction loss performance function measures the network's performance equal to the negative log probability of the target with the input distribution. More...

#include <reconstruction_loss.hpp>

Public Member Functions
	ReconstructionLoss ()
	Create the ReconstructionLoss object.
template<typename PredictionType , typename TargetType >
PredictionType::elem_type	Forward (const PredictionType &prediction, const TargetType &target)
	Computes the reconstruction loss. More...
template<typename PredictionType , typename TargetType , typename LossType >
void	Backward (const PredictionType &prediction, const TargetType &target, LossType &loss)
	Ordinary feed backward pass of a neural network. More...
OutputDataType &	OutputParameter () const
	Get the output parameter.
OutputDataType &	OutputParameter ()
	Modify the output parameter.
template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer.

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat, typename DistType = BernoulliDistribution<InputDataType>>
class mlpack::ann::ReconstructionLoss< InputDataType, OutputDataType, DistType >

The reconstruction loss performance function measures the network's performance equal to the negative log probability of the target with the input distribution.

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).
DistType	The type of distribution parametrized by the input.

Member Function Documentation

Backward()

template<typename InputDataType , typename OutputDataType , typename DistType >

template<typename PredictionType , typename TargetType , typename LossType >

void mlpack::ann::ReconstructionLoss< InputDataType, OutputDataType, DistType >::Backward	(	const PredictionType &	prediction,
		const TargetType &	target,
		LossType &	loss
	)

Ordinary feed backward pass of a neural network.

Parameters

prediction	Predictions used for evaluating the specified loss function.
target	The target matrix.
loss	The calculated error.

Forward()

template<typename InputDataType , typename OutputDataType , typename DistType >

template<typename PredictionType , typename TargetType >

PredictionType::elem_type mlpack::ann::ReconstructionLoss< InputDataType, OutputDataType, DistType >::Forward	(	const PredictionType &	prediction,
		const TargetType &	target
	)

Computes the reconstruction loss.

Parameters

prediction	Predictions used for evaluating the specified loss function.
target	The target matrix.

---

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

• src/mlpack/methods/ann/loss_functions/reconstruction_loss.hpp
• src/mlpack/methods/ann/loss_functions/reconstruction_loss_impl.hpp