OpenNN::NeuralParametersNorm Class Reference

#include <neural_parameters_norm.h>

Inheritance diagram for OpenNN::NeuralParametersNorm:

Public Member Functions
	NeuralParametersNorm (void)
	NeuralParametersNorm (NeuralNetwork *)
	NeuralParametersNorm (const tinyxml2::XMLDocument &)
virtual	~NeuralParametersNorm (void)
const double &	get_neural_parameters_norm_weight (void) const
void	set_neural_parameters_norm_weight (const double &)
void	set_default (void)
void	check (void) const
double	calculate_performance (void) const
Vector< double >	calculate_gradient (void) const
Matrix< double >	calculate_Hessian (void) const
double	calculate_performance (const Vector< double > &) const
Vector< double >	calculate_gradient (const Vector< double > &) const
Matrix< double >	calculate_Hessian (const Vector< double > &) const
std::string	write_performance_term_type (void) const
std::string	write_information (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 double	calculate_generalization_performance (void) 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	to_string (void) const
size_t	calculate_Kronecker_delta (const size_t &, const size_t &) const

Private Attributes
double	neural_parameters_norm_weight

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 neural parameters norm performance term. This performance term is very useful as a regularization functional in data modeling, optimal control or inverse problems.

Definition at line 40 of file neural_parameters_norm.h.

Constructor & Destructor Documentation

OpenNN::NeuralParametersNorm::NeuralParametersNorm ( void  )

explicit

Default constructor. It creates a neural parameters norm functional not associated to any neural network. It also initializes all the rest of class members to their default values.

Definition at line 27 of file neural_parameters_norm.cpp.

OpenNN::NeuralParametersNorm::NeuralParametersNorm ( NeuralNetwork *  new_neural_network_pointer )

explicit

Neural network constructor. It creates a neural parameters norm functional associated to a neural network. 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 41 of file neural_parameters_norm.cpp.

OpenNN::NeuralParametersNorm::NeuralParametersNorm ( const tinyxml2::XMLDocument &  neural_parameters_norm_document )

explicit

XML constructor. It creates a neural parameters norm object not associated to any neural network. The object members are loaded by means of a XML document-> Please be careful with the format of that file, which is specified in the OpenNN manual.

Parameters

neural_parameters_norm_document

TinyXML document with the neural parameters norm elements.

Definition at line 56 of file neural_parameters_norm.cpp.

OpenNN::NeuralParametersNorm::~NeuralParametersNorm ( void  )

virtual

Destructor. This destructor does not delete any pointer.

Definition at line 70 of file neural_parameters_norm.cpp.

Member Function Documentation

Vector< double > OpenNN::NeuralParametersNorm::calculate_gradient ( void  ) const

virtual

Calculates the objective gradient by means of the back-propagation algorithm, and returns it in a single vector of size the number of neural parameters.

Todo:

Case including independent parameters.

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 199 of file neural_parameters_norm.cpp.

Vector< double > OpenNN::NeuralParametersNorm::calculate_gradient ( const Vector< double > &  parameters ) const

virtual

Returns the default gradient vector of the performance term. It uses numerical differentiation.

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 283 of file neural_parameters_norm.cpp.

Matrix< double > OpenNN::NeuralParametersNorm::calculate_Hessian ( void  ) const

virtual

Calculates the objective Hessian by means of the back-propagation algorithm, and returns it in a single symmetric matrix of size the number of multilayer perceptron parameters.

Todo:

Second derivatives.

Case including independent parameters.

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 225 of file neural_parameters_norm.cpp.

Matrix< double > OpenNN::NeuralParametersNorm::calculate_Hessian ( const Vector< double > &  parameters ) const

virtual

Todo:

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 313 of file neural_parameters_norm.cpp.

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

virtual

Returns the performance of this peformance term. It is equal to the weighted norm of the parameters from the associated neural network.

Implements OpenNN::PerformanceTerm.

Definition at line 174 of file neural_parameters_norm.cpp.

double OpenNN::NeuralParametersNorm::calculate_performance ( const Vector< double > &  parameters ) const

virtual

Returns the neural parameters norm value of a neural network for a vector of parameters. It does not set that vector of parameters to the neural network.

Parameters

parameters

Vector of parameters for the neural network associated to the performance term.

Implements OpenNN::PerformanceTerm.

Definition at line 249 of file neural_parameters_norm.cpp.

void OpenNN::NeuralParametersNorm::check ( void  ) const

virtual

Checks that there is a neural network associated to this performance term, and that there is a multilayer perceptron in the neural network. If some of the above conditions is not hold, the method throws an exception.

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 119 of file neural_parameters_norm.cpp.

void OpenNN::NeuralParametersNorm::from_XML ( const tinyxml2::XMLDocument &  document )

virtual

Loads a sum squared error object from a XML document.

Parameters

document

TinyXML document containing the object members.

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 435 of file neural_parameters_norm.cpp.

void OpenNN::NeuralParametersNorm::set_default ( void  )

virtual

Sets the default values for the neural parameters norm object:

• Neural parameters norm weight: 0.1.
• Display: true.

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 105 of file neural_parameters_norm.cpp.

std::string OpenNN::NeuralParametersNorm::write_information ( void  ) const

virtual

Returns a string with the default information of the performance term. It will be used by the training strategy to monitor the training process. By default this information is empty.

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 375 of file neural_parameters_norm.cpp.

std::string OpenNN::NeuralParametersNorm::write_performance_term_type ( void  ) const

virtual

Returns a string with the name of the neural parameters norm performance type, "NEURAL_PARAMETERS_NORM".

Reimplemented from OpenNN::PerformanceTerm.

Definition at line 367 of file neural_parameters_norm.cpp.

---

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

• neural_parameters_norm.h
• neural_parameters_norm.cpp