mlpack::ann::PoissonNLLLoss< InputDataType, OutputDataType > Class Template Reference

Implementation of the Poisson negative log likelihood loss. More...

#include <poisson_nll_loss.hpp>

Public Member Functions
	PoissonNLLLoss (const bool logInput=true, const bool full=false, const typename InputDataType::elem_type eps=1e-08, const bool mean=true)
	Create the PoissonNLLLoss object. More...
template<typename PredictionType , typename TargetType >
InputDataType::elem_type	Forward (const PredictionType &prediction, const TargetType &target)
	Computes the Poisson negative log likelihood 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...
InputDataType &	InputParameter () const
	Get the input parameter.
InputDataType &	InputParameter ()
	Modify the input parameter.
OutputDataType &	OutputParameter () const
	Get the output parameter.
OutputDataType &	OutputParameter ()
	Modify the output parameter.
bool	LogInput () const
	Get the value of logInput. More...
bool &	LogInput ()
	Modify the value of logInput. More...
bool	Full () const
	Get the value of full. More...
bool &	Full ()
	Modify the value of full. More...
InputDataType::elem_type	Eps () const
	Get the value of eps. More...
InputDataType::elem_type &	Eps ()
	Modify the value of eps. More...
bool	Mean () const
	Get the value of mean. More...
bool &	Mean ()
	Modify the value of mean. More...
template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer.

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
class mlpack::ann::PoissonNLLLoss< InputDataType, OutputDataType >

Implementation of the Poisson negative log likelihood loss.

This loss function expects input for each class. It also expects a class index, in the range between 1 and the number of classes, as target when calling the Forward function.

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

PoissonNLLLoss()

template<typename InputDataType , typename OutputDataType >

mlpack::ann::PoissonNLLLoss< InputDataType, OutputDataType >::PoissonNLLLoss	(	const bool	logInput = true,
		const bool	full = false,
		const typename InputDataType::elem_type	eps = 1e-08,
		const bool	mean = true
	)

Create the PoissonNLLLoss object.

Parameters

logInput	If true the loss is computed as \( \exp(input) - target \cdot input \), if false then the loss is \( input - target \cdot \log(input + eps) \).
full	Boolean value that determines whether to include Stirling's approximation term.
eps	A small value to prevent 0 in denominators and logarithms.
mean	When true, mean loss is computed otherwise total loss.

Member Function Documentation

Backward()

template<typename InputDataType , typename OutputDataType >

template<typename PredictionType , typename TargetType , typename LossType >

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

Ordinary feed backward pass of a neural network.

The Poisson Negative Log Likelihood loss function expects the input for each class. It expects a class index, in the range between 1 and the number of classes, as target when calling the Forward function.

Parameters

prediction	Predictions used for evaluating the specified loss function.
target	The target vector, that contains the class index in the range between 1 and the number of classes.
loss	The calculated error.

Eps() [1/2]

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

InputDataType::elem_type mlpack::ann::PoissonNLLLoss< InputDataType, OutputDataType >::Eps ( ) const

inline

Get the value of eps.

eps is a small value required to prevent 0 in logarithms and denominators.

Eps() [2/2]

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

InputDataType::elem_type& mlpack::ann::PoissonNLLLoss< InputDataType, OutputDataType >::Eps ( )

inline

Modify the value of eps.

eps is a small value required to prevent 0 in logarithms and denominators.

Forward()

template<typename InputDataType , typename OutputDataType >

template<typename PredictionType , typename TargetType >

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

Computes the Poisson negative log likelihood Loss.

Parameters

prediction	Predictions used for evaluating the specified loss function.
target	The target vector, that contains the class index in the range between 1 and the number of classes.

Full() [1/2]

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

bool mlpack::ann::PoissonNLLLoss< InputDataType, OutputDataType >::Full ( ) const

inline

Get the value of full.

full is a boolean value that determines whether to include Stirling's approximation term.

Full() [2/2]

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

bool& mlpack::ann::PoissonNLLLoss< InputDataType, OutputDataType >::Full ( )

inline

Modify the value of full.

full is a boolean value that determines whether to include Stirling's approximation term.

LogInput() [1/2]

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

bool mlpack::ann::PoissonNLLLoss< InputDataType, OutputDataType >::LogInput ( ) const

inline

Get the value of logInput.

logInput is a boolean value that tells if logits are given as input.

LogInput() [2/2]

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

bool& mlpack::ann::PoissonNLLLoss< InputDataType, OutputDataType >::LogInput ( )

inline

Modify the value of logInput.

logInput is a boolean value that tells if logits are given as input.

Mean() [1/2]

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

bool mlpack::ann::PoissonNLLLoss< InputDataType, OutputDataType >::Mean ( ) const

inline

Get the value of mean.

It's a boolean value that tells if mean of the total loss has to be taken.

Mean() [2/2]

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

bool& mlpack::ann::PoissonNLLLoss< InputDataType, OutputDataType >::Mean ( )

inline

Modify the value of mean.

It's a boolean value that tells if mean of the total loss has to be taken.

---

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

• src/mlpack/methods/ann/loss_functions/poisson_nll_loss.hpp
• src/mlpack/methods/ann/loss_functions/poisson_nll_loss_impl.hpp