OpenNN::InverseSumSquaredError Class Reference

#include <inverse_sum_squared_error.h>

Inheritance diagram for OpenNN::InverseSumSquaredError:

Public Types
enum	UnknownsMethod { LookUpTable, IndependentParametersValues }

Public Member Functions
	InverseSumSquaredError (void)
	InverseSumSquaredError (NeuralNetwork *)
	InverseSumSquaredError (NeuralNetwork *, MathematicalModel *, DataSet *)
	InverseSumSquaredError (const tinyxml2::XMLDocument &)
virtual	~InverseSumSquaredError (void)
const UnknownsMethod &	get_unknowns_method (void) const
std::string	write_unknowns_method (void) const
void	set_unknowns_method (const UnknownsMethod &)
void	set_unknowns_method (const std::string &)
void	set_default (void)
void	check (void) const
double	calculate_performance (void) const
double	calculate_performance (const Vector< double > &) const
double	calculate_generalization_performance (void) const
std::string	write_performance_term_type (void) const
tinyxml2::XMLDocument *	to_XML (void) const
void	from_XML (const tinyxml2::XMLDocument &)
Public Member Functions inherited from OpenNN::PerformanceTerm
	PerformanceTerm (void)
	PerformanceTerm (NeuralNetwork *)
	PerformanceTerm (DataSet *)
	PerformanceTerm (MathematicalModel *)
	PerformanceTerm (NeuralNetwork *, DataSet *)
	PerformanceTerm (NeuralNetwork *, MathematicalModel *)
	PerformanceTerm (NeuralNetwork *, MathematicalModel *, DataSet *)
	PerformanceTerm (const tinyxml2::XMLDocument &)
	PerformanceTerm (const PerformanceTerm &)
virtual	~PerformanceTerm (void)
virtual PerformanceTerm &	operator= (const PerformanceTerm &)
virtual bool	operator== (const PerformanceTerm &) const
NeuralNetwork *	get_neural_network_pointer (void) const
MathematicalModel *	get_mathemtaical_model_pointer (void) const
DataSet *	get_data_set_pointer (void) const
NumericalDifferentiation *	get_numerical_differentiation_pointer (void) const
const bool &	get_display (void) const
bool	has_neural_network (void) const
bool	has_mathematical_model (void) const
bool	has_data_set (void) const
bool	has_numerical_differentiation (void) const
virtual void	set (void)
virtual void	set (NeuralNetwork *)
virtual void	set (DataSet *)
virtual void	set (MathematicalModel *)
virtual void	set (NeuralNetwork *, DataSet *)
virtual void	set (NeuralNetwork *, MathematicalModel *)
virtual void	set (NeuralNetwork *, MathematicalModel *, DataSet *)
void	set (const PerformanceTerm &)
virtual void	set_neural_network_pointer (NeuralNetwork *)
virtual void	set_mathematical_model_pointer (MathematicalModel *)
virtual void	set_data_set_pointer (DataSet *)
void	set_numerical_differentiation_pointer (NumericalDifferentiation *)
void	set_display (const bool &)
void	construct_numerical_differentiation (void)
void	delete_numerical_differentiation_pointer (void)
Vector< Vector< double > >	calculate_layers_delta (const Vector< Vector< double > > &, const Vector< double > &) const
Vector< Vector< double > >	calculate_layers_delta (const Vector< Vector< double > > &, const Vector< double > &, const Vector< double > &) const
Matrix< Matrix< double > >	calculate_interlayers_Delta (const Vector< Vector< double > > &, const Vector< Vector< double > > &, const Matrix< Matrix< double > > &, const Vector< double > &, const Matrix< double > &, const Vector< Vector< double > > &) const
Vector< double >	calculate_point_gradient (const Vector< double > &, const Vector< Vector< double > > &, const Vector< Vector< double > > &) const
Vector< double >	calculate_point_gradient (const Vector< Matrix< double > > &, const Vector< Vector< double > > &) const
Matrix< double >	calculate_point_Hessian (const Vector< Vector< double > > &, const Vector< Vector< Vector< double > > > &, const Matrix< Matrix< double > > &, const Vector< Vector< double > > &, const Matrix< Matrix< double > > &) const
virtual Vector< double >	calculate_gradient (void) const
virtual Vector< double >	calculate_gradient (const Vector< double > &) const
virtual Matrix< double >	calculate_Hessian (void) const
virtual Matrix< double >	calculate_Hessian (const Vector< double > &) const
virtual Vector< double >	calculate_terms (void) const
virtual Vector< double >	calculate_terms (const Vector< double > &) const
virtual Matrix< double >	calculate_terms_Jacobian (void) const
virtual PerformanceTerm::FirstOrderTerms	calculate_first_order_terms (void) const
virtual std::string	write_information (void) const
virtual std::string	to_string (void) const
size_t	calculate_Kronecker_delta (const size_t &, const size_t &) const

Private Attributes
UnknownsMethod	unknowns_method

Additional Inherited Members
Protected Attributes inherited from OpenNN::PerformanceTerm
NeuralNetwork *	neural_network_pointer
DataSet *	data_set_pointer
MathematicalModel *	mathematical_model_pointer
NumericalDifferentiation *	numerical_differentiation_pointer
bool	display

Detailed Description

This class represents the concept of sum squared error for inverse problems. It measures the difference between the outputs from a mathematical model and the targets in a data set. This performance term is used in inverse problems.

Definition at line 39 of file inverse_sum_squared_error.h.

Constructor & Destructor Documentation

OpenNN::InverseSumSquaredError::InverseSumSquaredError ( void  )

explicit

Default constructor. It creates an inverse sum squared error performance term not associated to any neural network and not measured on any mathematical model and data set. It also initializes all the rest of class members to their default values.

Definition at line 29 of file inverse_sum_squared_error.cpp.

OpenNN::InverseSumSquaredError::InverseSumSquaredError ( NeuralNetwork *  new_neural_network_pointer )

explicit

Neural network constructor. It creates an inverse sum squared error associated to a neural network but neither measured on a mathematical model nor on a data set. It also initializes all the rest of class members to their default values.

Parameters

new_neural_network_pointer

Pointer to a neural network object.

Definition at line 43 of file inverse_sum_squared_error.cpp.

OpenNN::InverseSumSquaredError::InverseSumSquaredError ( NeuralNetwork *  new_neural_network_pointer, MathematicalModel *  new_mathematical_model_pointer, DataSet *  new_data_set_pointer  )

explicit

Neural network, mathematical model and data set constructor. It creates an inverse sum squared error associated to a neural network and measured on a mathematical model and a data set. It also initializes all the rest of class members to their default values.

Parameters

new_neural_network_pointer	Pointer to a neural network object.
new_mathematical_model_pointer	Pointer to a mathematical model object.
new_data_set_pointer	Pointer to a data set object.

Definition at line 61 of file inverse_sum_squared_error.cpp.

OpenNN::InverseSumSquaredError::InverseSumSquaredError ( const tinyxml2::XMLDocument &  inverse_sum_squared_error_document )

explicit

XML constructor. It creates an inverse sum squared error performance term not associated to any neural network and not measured on any mathematical model and data set. It initializes all the member data from a XML document.

Parameters

inverse_sum_squared_error_document

Pointer to a TinyXML document containing the inverse sum squared error data.

Definition at line 77 of file inverse_sum_squared_error.cpp.

OpenNN::InverseSumSquaredError::~InverseSumSquaredError ( void  )

virtual

Destructor. It does not delete any object.

Definition at line 91 of file inverse_sum_squared_error.cpp.

Member Function Documentation

double OpenNN::InverseSumSquaredError::calculate_generalization_performance ( void  ) const

virtual

Todo:

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 353 of file inverse_sum_squared_error.cpp.

double OpenNN::InverseSumSquaredError::calculate_performance ( void  ) const

virtual

Todo:

Implements OpenNN::PerformanceTerm.

Definition at line 281 of file inverse_sum_squared_error.cpp.

void OpenNN::InverseSumSquaredError::check ( void  ) const

virtual

Checks that there are a neural network, a mathemacial model and a data set associated to the inverse sum squared error. If some of the above conditions is not hold, the method throws an exception.

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 203 of file inverse_sum_squared_error.cpp.

void OpenNN::InverseSumSquaredError::from_XML ( const tinyxml2::XMLDocument &  )

virtual

Todo:

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 495 of file inverse_sum_squared_error.cpp.

void OpenNN::InverseSumSquaredError::set_default ( void  )

virtual

Sets the default values of the inverse sum squared error:

• Unknowns method: Independent parameters values.
• Display: true.

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 190 of file inverse_sum_squared_error.cpp.

void OpenNN::InverseSumSquaredError::set_unknowns_method

(

const UnknownsMethod &

new_unknowns_method

)

This sets a new the method for entering the unknown values or functions into the mathematical model.

Parameters

new_unknowns_method

Unknowns method (independent parameters, look-up table, ...).

Definition at line 148 of file inverse_sum_squared_error.cpp.

void OpenNN::InverseSumSquaredError::set_unknowns_method

(

const std::string &

new_unknowns_method

)

This sets a new the method for entering the unknown values or functions into the mathematical model.

Parameters

new_unknowns_method

String with the name of the unknowns method (independent parameters, look-up table, ...).

Definition at line 159 of file inverse_sum_squared_error.cpp.

tinyxml2::XMLDocument * OpenNN::InverseSumSquaredError::to_XML ( void  ) const

virtual

Serializes the inverse sum squared error object into a XML document of the TinyXML library. See the OpenNN manual for more information about the format of this document->

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 444 of file inverse_sum_squared_error.cpp.

---

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

• inverse_sum_squared_error.h
• inverse_sum_squared_error.cpp