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

Margin ranking loss measures the loss given inputs and a label vector with values of 1 or -1. More...

#include <margin_ranking_loss.hpp>

Public Member Functions
	MarginRankingLoss (const double margin=1.0)
	Create the MarginRankingLoss object with Hyperparameter margin. More...
template<typename PredictionType , typename TargetType >
PredictionType::elem_type	Forward (const PredictionType &prediction, const TargetType &target)
	Computes the Margin Ranking Loss function. 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.
double	Margin () const
	Get the margin parameter.
double &	Margin ()
	Modify the margin 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>
class mlpack::ann::MarginRankingLoss< InputDataType, OutputDataType >

Margin ranking loss measures the loss given inputs and a label vector with values of 1 or -1.

If the label is 1 then the first input should be ranked higher than the second input at a distance larger than a margin, and vice- versa if the label is -1.

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

MarginRankingLoss()

template<typename InputDataType , typename OutputDataType >

mlpack::ann::MarginRankingLoss< InputDataType, OutputDataType >::MarginRankingLoss

(

const double

margin = 1.0

)

Create the MarginRankingLoss object with Hyperparameter margin.

Hyperparameter margin defines a minimum distance between correctly ranked samples.

Member Function Documentation

Backward()

template<typename InputDataType , typename OutputDataType >

template<typename PredictionType , typename TargetType , typename LossType >

void mlpack::ann::MarginRankingLoss< InputDataType, OutputDataType >::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 label vector which contains -1 or 1 values.
loss	The calculated error.

Forward()

template<typename InputDataType , typename OutputDataType >

template<typename PredictionType , typename TargetType >

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

Computes the Margin Ranking Loss function.

Parameters

prediction	Predictions used for evaluating the specified loss function.
target	The label vector which contains values of -1 or 1.

---

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

• src/mlpack/methods/ann/loss_functions/margin_ranking_loss.hpp
• src/mlpack/methods/ann/loss_functions/margin_ranking_loss_impl.hpp