KLDivergence< InputDataType, OutputDataType > Class Template Reference

The Kullback–Leibler divergence is often used for continuous distributions (direct regression). More...

Public Member Functions
	KLDivergence (const bool takeMean=false)
	Create the Kullback–Leibler Divergence object with the specified parameters. 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...
template < typename PredictionType , typename TargetType >
PredictionType::elem_type	Forward (const PredictionType &prediction, const TargetType &target)
	Computes the Kullback–Leibler divergence error function. More...
OutputDataType &	OutputParameter () const
	Get the output parameter. More...
OutputDataType &	OutputParameter ()
	Modify the output parameter. More...
template < typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the loss function. More...
bool	TakeMean () const
	Get the value of takeMean. More...
bool &	TakeMean ()
	Modify the value of takeMean. More...

Detailed Description

template

<

typename

InputDataType

=

arma::mat

,

typename

OutputDataType

=

arma::mat

>

class mlpack::ann::KLDivergence< InputDataType, OutputDataType >

The Kullback–Leibler divergence is often used for continuous distributions (direct regression).

For more information, see the following paper.

article{Kullback1951,
  title   = {On Information and Sufficiency},
  author  = {S. Kullback, R.A. Leibler},
  journal = {The Annals of Mathematical Statistics},
  year    = {1951}
}

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).

Definition at line 45 of file kl_divergence.hpp.

Constructor & Destructor Documentation

KLDivergence()

KLDivergence

(

const bool

takeMean = false

)

Create the Kullback–Leibler Divergence object with the specified parameters.

Parameters

takeMean

Boolean variable to specify whether to take mean or not.

Member Function Documentation

Backward()

void 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 vector.
loss	The calculated error.

Forward()

PredictionType::elem_type Forward	(	const PredictionType &	prediction,
		const TargetType &	target
	)

Computes the Kullback–Leibler divergence error function.

Parameters

prediction	Predictions used for evaluating the specified loss function.
target	Target data to compare with.

OutputParameter() [1/2]

OutputDataType& OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 81 of file kl_divergence.hpp.

OutputParameter() [2/2]

OutputDataType& OutputParameter ( )

inline

Modify the output parameter.

Definition at line 83 of file kl_divergence.hpp.

serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

Serialize the loss function.

Referenced by KLDivergence< InputDataType, OutputDataType >::TakeMean().

TakeMean() [1/2]

bool TakeMean ( ) const

inline

Get the value of takeMean.

Definition at line 86 of file kl_divergence.hpp.

TakeMean() [2/2]

bool& TakeMean ( )

inline

Modify the value of takeMean.

Definition at line 88 of file kl_divergence.hpp.

References KLDivergence< InputDataType, OutputDataType >::serialize().

---

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

• /home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/loss_functions/kl_divergence.hpp