xmm::ClassParameters< HMM > Class Template Reference

Parameters specific to each class of a Hidden Markov Model. More...

#include <xmmHmmParameters.hpp>

Inheritance diagram for xmm::ClassParameters< HMM >:

Collaboration diagram for xmm::ClassParameters< HMM >:

Public Member Functions
	ClassParameters ()
	Default Constructor. More...
	ClassParameters (ClassParameters const &src)
	Copy Constructor. More...
	ClassParameters (Json::Value const &root)
	Constructor from Json Structure. More...
ClassParameters &	operator= (ClassParameters const &src)
	Assignment. More...
Json I/O
Json::Value	toJson () const
	Write the object to a JSON Structure. More...
virtual void	fromJson (Json::Value const &root)
	Read the object from a JSON Structure. More...

Public Attributes
bool	changed = false
	specifies if parameters have changed (model is invalid) More...
Attribute< unsigned int >	states
	Number of hidden states. More...
Attribute< unsigned int >	gaussians
	Number of Gaussian Mixture Components. More...
Attribute< double >	relative_regularization
	Offset Added to the diagonal of covariance matrices for convergence (Relative to Data Variance) More...
Attribute< double >	absolute_regularization
	Offset Added to the diagonal of covariance matrices for convergence (minimum value) More...
Attribute< GaussianDistribution::CovarianceMode >	covariance_mode
	Covariance Mode. More...
Attribute< HMM::TransitionMode >	transition_mode
	Transition matrix of the model (left-right vs ergodic) More...
Attribute< HMM::RegressionEstimator >	regression_estimator
	Type of regression estimator. More...
Attribute< bool >	hierarchical
	specifies if the decoding algorithm is hierarchical or class-conditional More...

Protected Member Functions
virtual void	onAttributeChange (AttributeBase *attr_pointer)
	notification function called when a member attribute is changed More...

Detailed Description

template<>
class xmm::ClassParameters< HMM >

Parameters specific to each class of a Hidden Markov Model.

Constructor & Destructor Documentation

xmm::ClassParameters< HMM >::ClassParameters

(

)

Default Constructor.

xmm::ClassParameters< HMM >::ClassParameters

(

ClassParameters< HMM > const &

src

)

Copy Constructor.

Parameters

src	Source Object

xmm::ClassParameters< HMM >::ClassParameters ( Json::Value const &  root )

explicit

Constructor from Json Structure.

Parameters

root	Json Value

Member Function Documentation

virtual void xmm::ClassParameters< HMM >::fromJson ( Json::Value const &  root )

virtual

Read the object from a JSON Structure.

Parameters

root	JSON value containing the object's information

Exceptions

JsonException

if the JSON value has a wrong format

Reimplemented in xmm::Configuration< HMM >.

virtual void xmm::ClassParameters< HMM >::onAttributeChange ( AttributeBase *  attr_pointer )

protectedvirtual

notification function called when a member attribute is changed

ClassParameters& xmm::ClassParameters< HMM >::operator=

(

ClassParameters< HMM > const &

src

)

Assignment.

Parameters

src	Source Object

Json::Value xmm::ClassParameters< HMM >::toJson

(

)

const

Write the object to a JSON Structure.

Returns

Json value containing the object's information

Member Data Documentation

Attribute<double> xmm::ClassParameters< HMM >::absolute_regularization

Offset Added to the diagonal of covariance matrices for convergence (minimum value)

bool xmm::ClassParameters< HMM >::changed = false

specifies if parameters have changed (model is invalid)

Attribute<GaussianDistribution::CovarianceMode> xmm::ClassParameters< HMM >::covariance_mode

Covariance Mode.

Attribute<unsigned int> xmm::ClassParameters< HMM >::gaussians

Number of Gaussian Mixture Components.

Attribute<bool> xmm::ClassParameters< HMM >::hierarchical

specifies if the decoding algorithm is hierarchical or class-conditional

Attribute<HMM::RegressionEstimator> xmm::ClassParameters< HMM >::regression_estimator

Type of regression estimator.

Attribute<double> xmm::ClassParameters< HMM >::relative_regularization

Offset Added to the diagonal of covariance matrices for convergence (Relative to Data Variance)

Attribute<unsigned int> xmm::ClassParameters< HMM >::states

Number of hidden states.

Attribute<HMM::TransitionMode> xmm::ClassParameters< HMM >::transition_mode

Transition matrix of the model (left-right vs ergodic)

---

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

• xmmHmmParameters.hpp