A single multivariate Gaussian distribution. More...

Public Member Functions
	GaussianDistribution ()
	Default constructor, which creates a Gaussian with zero dimension. More...

	GaussianDistribution (const size_t dimension)
	Create a Gaussian distribution with zero mean and identity covariance with the given dimensionality. More...

	GaussianDistribution (const arma::vec &mean, const arma::mat &covariance)
	Create a Gaussian distribution with the given mean and covariance. More...

const arma::mat &	Covariance () const
	Return the covariance matrix. More...

void	Covariance (const arma::mat &covariance)
	Set the covariance. More...

void	Covariance (arma::mat &&covariance)

size_t	Dimensionality () const
	Return the dimensionality of this distribution. More...

double	LogProbability (const arma::vec &observation) const
	Return the log probability of the given observation. More...

void	LogProbability (const arma::mat &x, arma::vec &logProbabilities) const
	Calculates the multivariate Gaussian log probability density function for each data point (column) in the given matrix. More...

const arma::vec &	Mean () const
	Return the mean. More...

arma::vec &	Mean ()
	Return a modifiable copy of the mean. More...

double	Probability (const arma::vec &observation) const
	Return the probability of the given observation. More...

void	Probability (const arma::mat &x, arma::vec &probabilities) const
	Calculates the multivariate Gaussian probability density function for each data point (column) in the given matrix. More...

arma::vec	Random () const
	Return a randomly generated observation according to the probability distribution defined by this object. More...

template<typename Archive >
void	Serialize (Archive &ar, const unsigned int)
	Serialize the distribution. More...

void	Train (const arma::mat &observations)
	Estimate the Gaussian distribution directly from the given observations. More...

void	Train (const arma::mat &observations, const arma::vec &probabilities)
	Estimate the Gaussian distribution from the given observations, taking into account the probability of each observation actually being from this distribution. More...

Private Member Functions
void	FactorCovariance ()
	This factors the covariance using arma::chol(). More...

Private Attributes
arma::mat	covariance
	Positive definite covariance of the distribution. More...

arma::mat	covLower
	Lower triangular factor of cov (e.g. cov = LL^T). More...

arma::mat	invCov
	Cached inverse of covariance. More...

double	logDetCov
	Cached logdet(cov). More...

arma::vec	mean
	Mean of the distribution. More...

Static Private Attributes
static const constexpr double	log2pi = 1.83787706640934533908193770912475883
	log(2pi) More...

Detailed Description

A single multivariate Gaussian distribution.

Definition at line 24 of file gaussian_distribution.hpp.

Constructor & Destructor Documentation

mlpack::distribution::GaussianDistribution::GaussianDistribution ( )

inline

Default constructor, which creates a Gaussian with zero dimension.

Definition at line 45 of file gaussian_distribution.hpp.

Referenced by GaussianDistribution().

mlpack::distribution::GaussianDistribution::GaussianDistribution ( const size_t dimension )

inline

Create a Gaussian distribution with zero mean and identity covariance with the given dimensionality.

Definition at line 51 of file gaussian_distribution.hpp.

References GaussianDistribution().

mlpack::distribution::GaussianDistribution::GaussianDistribution	(	const arma::vec &	mean,
		const arma::mat &	covariance
	)

Create a Gaussian distribution with the given mean and covariance.

covariance is expected to be positive definite.

Member Function Documentation

const arma::mat& mlpack::distribution::GaussianDistribution::Covariance ( ) const

inline

Return the covariance matrix.

Definition at line 136 of file gaussian_distribution.hpp.

References covariance.

Referenced by mlpack::distribution::RegressionDistribution::RegressionDistribution().

void mlpack::distribution::GaussianDistribution::Covariance ( const arma::mat & covariance )

Set the covariance.

void mlpack::distribution::GaussianDistribution::Covariance ( arma::mat && covariance )

size_t mlpack::distribution::GaussianDistribution::Dimensionality ( ) const

inline

Return the dimensionality of this distribution.

Definition at line 69 of file gaussian_distribution.hpp.

void mlpack::distribution::GaussianDistribution::FactorCovariance ( )

private

This factors the covariance using arma::chol().

The function assumes that the given matrix is factorizable via the Cholesky decomposition. If not, a std::runtime_error will be thrown.

Referenced by Serialize().

double mlpack::distribution::GaussianDistribution::LogProbability ( const arma::vec & observation ) const

Return the log probability of the given observation.

Referenced by Probability().

void mlpack::distribution::GaussianDistribution::LogProbability	(	const arma::mat &	x,
		arma::vec &	logProbabilities
	)		const

inline

Calculates the multivariate Gaussian log probability density function for each data point (column) in the given matrix.

Parameters

x	List of observations.
probabilities	Output log probabilities for each input observation.

Definition at line 177 of file gaussian_distribution.hpp.

References invCov, log2pi, logDetCov, and mean.

const arma::vec& mlpack::distribution::GaussianDistribution::Mean ( ) const

inline

Return the mean.

Definition at line 126 of file gaussian_distribution.hpp.

References mean.

arma::vec& mlpack::distribution::GaussianDistribution::Mean ( )

inline

Return a modifiable copy of the mean.

Definition at line 131 of file gaussian_distribution.hpp.

References mean.

double mlpack::distribution::GaussianDistribution::Probability ( const arma::vec & observation ) const

inline

Return the probability of the given observation.

Definition at line 74 of file gaussian_distribution.hpp.

References LogProbability().

void mlpack::distribution::GaussianDistribution::Probability	(	const arma::mat &	x,
		arma::vec &	probabilities
	)		const

inline

Calculates the multivariate Gaussian probability density function for each data point (column) in the given matrix.

Parameters

x	List of observations.
probabilities	Output probabilities for each input observation.

Definition at line 91 of file gaussian_distribution.hpp.

References LogProbability(), Random(), and Train().

arma::vec mlpack::distribution::GaussianDistribution::Random ( ) const

Return a randomly generated observation according to the probability distribution defined by this object.

Returns: Random observation from this Gaussian distribution.

Referenced by Probability().

template<typename Archive >

void mlpack::distribution::GaussianDistribution::Serialize	(	Archive &	ar,
		const unsigned	int
	)

inline

Serialize the distribution.

Definition at line 149 of file gaussian_distribution.hpp.

References mlpack::data::CreateNVP(), and FactorCovariance().

void mlpack::distribution::GaussianDistribution::Train ( const arma::mat & observations )

Estimate the Gaussian distribution directly from the given observations.

Parameters

observations List of observations.

Referenced by Probability().

void mlpack::distribution::GaussianDistribution::Train	(	const arma::mat &	observations,
		const arma::vec &	probabilities
	)

Estimate the Gaussian distribution from the given observations, taking into account the probability of each observation actually being from this distribution.

Member Data Documentation

arma::mat mlpack::distribution::GaussianDistribution::covariance

private

Positive definite covariance of the distribution.

Definition at line 30 of file gaussian_distribution.hpp.

Referenced by Covariance().

arma::mat mlpack::distribution::GaussianDistribution::covLower

private

Lower triangular factor of cov (e.g. cov = LL^T).

Definition at line 32 of file gaussian_distribution.hpp.

arma::mat mlpack::distribution::GaussianDistribution::invCov

private

Cached inverse of covariance.

Definition at line 34 of file gaussian_distribution.hpp.

Referenced by LogProbability().

const constexpr double mlpack::distribution::GaussianDistribution::log2pi = 1.83787706640934533908193770912475883

staticprivate

log(2pi)

Definition at line 39 of file gaussian_distribution.hpp.

Referenced by LogProbability().

double mlpack::distribution::GaussianDistribution::logDetCov

private

Cached logdet(cov).

Definition at line 36 of file gaussian_distribution.hpp.

Referenced by LogProbability().

arma::vec mlpack::distribution::GaussianDistribution::mean

private

Mean of the distribution.

Definition at line 28 of file gaussian_distribution.hpp.

Referenced by LogProbability(), and Mean().

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

src/mlpack/core/dists/gaussian_distribution.hpp

Public Member Functions

Private Member Functions

Private Attributes

Static Private Attributes

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation