#include <training_strategy.h>

Classes
struct	Results

Public Types
enum	InitializationType { NO_INITIALIZATION, RANDOM_SEARCH, EVOLUTIONARY_ALGORITHM, USER_INITIALIZATION }

enum	MainType { NO_MAIN, GRADIENT_DESCENT, CONJUGATE_GRADIENT, QUASI_NEWTON_METHOD, LEVENBERG_MARQUARDT_ALGORITHM, USER_MAIN }

enum	RefinementType { NO_REFINEMENT, NEWTON_METHOD, USER_REFINEMENT }

Public Member Functions
	TrainingStrategy (void)

	TrainingStrategy (PerformanceFunctional *)

	TrainingStrategy (const tinyxml2::XMLDocument &)

	TrainingStrategy (const std::string &)

virtual	~TrainingStrategy (void)

void	check_performance_functional (void) const

void	check_training_algorithms (void) const

void	initialize_random (void)

PerformanceFunctional *	get_performance_functional_pointer (void) const

bool	has_performance_functional (void) const

RandomSearch *	get_random_search_pointer (void) const

EvolutionaryAlgorithm *	get_evolutionary_algorithm_pointer (void) const

GradientDescent *	get_gradient_descent_pointer (void) const

ConjugateGradient *	get_conjugate_gradient_pointer (void) const

QuasiNewtonMethod *	get_quasi_Newton_method_pointer (void) const

LevenbergMarquardtAlgorithm *	get_Levenberg_Marquardt_algorithm_pointer (void) const

NewtonMethod *	get_Newton_method_pointer (void) const

const InitializationType &	get_initialization_type (void) const

const MainType &	get_main_type (void) const

const RefinementType &	get_refinement_type (void) const

std::string	write_initialization_type (void) const

std::string	write_main_type (void) const

std::string	write_refinement_type (void) const

std::string	write_initialization_type_text (void) const

std::string	write_main_type_text (void) const

std::string	write_refinement_type_text (void) const

const bool &	get_display (void) const

void	set (void)

void	set (PerformanceFunctional *)

virtual void	set_default (void)

void	set_performance_functional_pointer (PerformanceFunctional *)

void	set_initialization_type (const InitializationType &)

void	set_main_type (const MainType &)

void	set_refinement_type (const RefinementType &)

void	set_initialization_type (const std::string &)

void	set_main_type (const std::string &)

void	set_refinement_type (const std::string &)

void	set_display (const bool &)

void	destruct_initialization (void)

void	destruct_main (void)

void	destruct_refinement (void)

Results	perform_training (void)

std::string	to_string (void) const

void	print (void) const

tinyxml2::XMLDocument *	to_XML (void) const

void	from_XML (const tinyxml2::XMLDocument &)

void	save (const std::string &) const

void	load (const std::string &)

Detailed Description

This class represents the concept of training strategy for a neural network. A training strategy is composed of three training algorithms:

Initialization training algorithm.
Main training algorithm.
Refinement trainining algorithm.

Definition at line 58 of file training_strategy.h.

Constructor & Destructor Documentation

OpenNN::TrainingStrategy::TrainingStrategy ( void )

explicit

Default constructor. It creates a training strategy object not associated to any performance functional object. It also constructs the main training algorithm object.

Definition at line 27 of file training_strategy.cpp.

OpenNN::TrainingStrategy::TrainingStrategy ( PerformanceFunctional * new_performance_functional_pointer )

explicit

Performance functional constructor. It creates a training strategy object associated to a performance functional object. It also constructs the main training algorithm object.

Parameters

new_performance_functional_pointer Pointer to a performance functional object.

Definition at line 52 of file training_strategy.cpp.

OpenNN::TrainingStrategy::TrainingStrategy ( const tinyxml2::XMLDocument & document )

explicit

XML constructor. It creates a training strategy object not associated to any performance functional object. It also loads the members of this object from a XML document.

Parameters

document Document of the TinyXML library.

Definition at line 77 of file training_strategy.cpp.

OpenNN::TrainingStrategy::TrainingStrategy ( const std::string & file_name )

explicit

File constructor. It creates a training strategy object associated to a performance functional object. It also loads the members of this object from a XML file.

Parameters

file_name Name of training strategy XML file.

Definition at line 104 of file training_strategy.cpp.

OpenNN::TrainingStrategy::~TrainingStrategy ( void )

virtual

Destructor. This destructor deletes the initialization, main and refinement training algorithm objects.

Definition at line 129 of file training_strategy.cpp.

Member Function Documentation

void OpenNN::TrainingStrategy::check_training_algorithms ( void ) const

Throws an exception if the training strategy does not have any initialization, main or refinement algorithms.

Definition at line 170 of file training_strategy.cpp.

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

Loads the members of this training strategy object from a XML document.

Parameters

document XML document of the TinyXML library.

Definition at line 1784 of file training_strategy.cpp.

ConjugateGradient * OpenNN::TrainingStrategy::get_conjugate_gradient_pointer ( void ) const

Returns a pointer to the conjugate gradient main algorithm. It also throws an exception if that pointer is NULL.

Definition at line 338 of file training_strategy.cpp.

const bool & OpenNN::TrainingStrategy::get_display ( void ) const

Returns true if messages from this class can be displayed on the screen, or false if messages from this class can't be displayed on the screen.

Definition at line 674 of file training_strategy.cpp.

EvolutionaryAlgorithm * OpenNN::TrainingStrategy::get_evolutionary_algorithm_pointer ( void ) const

Returns a pointer to the evolutionary algorithm initialization algorithm. It also throws an exception if that pointer is NULL.

Definition at line 294 of file training_strategy.cpp.

GradientDescent * OpenNN::TrainingStrategy::get_gradient_descent_pointer ( void ) const

Returns a pointer to the gradient descent main algorithm. It also throws an exception if that pointer is NULL.

Definition at line 316 of file training_strategy.cpp.

LevenbergMarquardtAlgorithm * OpenNN::TrainingStrategy::get_Levenberg_Marquardt_algorithm_pointer ( void ) const

Returns a pointer to the Levenberg-Marquardt main algorithm. It also throws an exception if that pointer is NULL.

Definition at line 382 of file training_strategy.cpp.

NewtonMethod * OpenNN::TrainingStrategy::get_Newton_method_pointer ( void ) const

Returns a pointer to the Newton method refinement algorithm. It also throws an exception if that pointer is NULL.

Definition at line 404 of file training_strategy.cpp.

QuasiNewtonMethod * OpenNN::TrainingStrategy::get_quasi_Newton_method_pointer ( void ) const

Returns a pointer to the Newton method main algorithm. It also throws an exception if that pointer is NULL.

Definition at line 360 of file training_strategy.cpp.

RandomSearch * OpenNN::TrainingStrategy::get_random_search_pointer ( void ) const

Returns a pointer to the random search initialization algorithm. It also throws an exception if that pointer is NULL.

Definition at line 272 of file training_strategy.cpp.

bool OpenNN::TrainingStrategy::has_performance_functional ( void ) const

Returns true if this training strategy has a performance functional associated, and false otherwise.

Definition at line 254 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::initialize_random ( void )

Initializes the initialization, main and refinement algorithms at random.

Todo:

Definition at line 192 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::load ( const std::string & file_name )

Loads a gradient descent object from a XML-type file. Please mind about the file format, wich is specified in the User's Guide.

Parameters

file_name Name of training algorithm XML-type file.

Definition at line 2050 of file training_strategy.cpp.

TrainingStrategy::Results OpenNN::TrainingStrategy::perform_training ( void )

This is the most important method of this class. It optimizes the performance functional of a neural network. The most general training strategy consists of three steps: initialization, main and refinement training processes. This method also returns a structure with the results from training.

Definition at line 1219 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::save ( const std::string & file_name ) const

Saves to a XML-type file the members of the training algorithm object.

Parameters

file_name Name of training algorithm XML-type file.

Definition at line 2034 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::set ( void )

Sets the performance functional pointer to NULL. It also destructs the initialization, main and refinement training algorithms. Finally, it sets the rest of members to their default values.

Definition at line 686 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::set ( PerformanceFunctional * new_performance_functional_pointer )

Sets a new performance functional pointer. It also destructs the initialization, main and refinement training algorithms. Finally, it sets the rest of members to their default values.

Parameters

new_performance_functional_pointer Pointer to a performance functional object.

Definition at line 705 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::set_default ( void )

virtual

Sets the members of the training strategy object to their default values:

Display: true.

Definition at line 1153 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::set_display ( const bool & new_display )

Sets a new display value. If it is set to true messages from this class are to be displayed on the screen; if it is set to false messages from this class are not to be displayed on the screen.

Parameters

new_display Display value.

Definition at line 1140 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::set_initialization_type ( const InitializationType & new_initialization_type )

Sets a new type of initialization training algorithm.

Parameters

new_initialization_type Type of initialization training algorithm.

Definition at line 722 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::set_initialization_type ( const std::string & new_initialization_type )

Sets a new initialization training algorithm from a string.

Parameters

new_initialization_type String with the initialization type.

Definition at line 885 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::set_main_type ( const MainType & new_main_type )

Sets a new type of main training algorithm.

Parameters

new_main_type Type of main training algorithm.

Definition at line 774 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::set_main_type ( const std::string & new_main_type )

Sets a new main training algorithm from a string containing the type.

Parameters

new_main_type String with the type of main training algorithm.

Definition at line 921 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::set_performance_functional_pointer ( PerformanceFunctional * new_performance_functional_pointer )

Sets a pointer to a performance functional object to be associated to the training strategy.

Parameters

new_performance_functional_pointer Pointer to a performance functional object.

Definition at line 998 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::set_refinement_type ( const RefinementType & new_refinement_type )

Sets a new type of refinement algorithm into this training strategy. Note that it destructs the current refinement algorithm object and constructs a new one.

Parameters

new_refinement_type Type of refinement training algorithm.

Definition at line 839 of file training_strategy.cpp.

void OpenNN::TrainingStrategy::set_refinement_type ( const std::string & new_refinement_type )

Sets a new refinement algorithm from a string. It destructs the previous refinement algorithm object and constructs a new object.

Parameters

new_refinement_type String with the refinement training algorithm type.

Definition at line 966 of file training_strategy.cpp.

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

Returns a default string representation in XML-type format of the training algorithm object. This containts the training operators, the training parameters, stopping criteria and other stuff.

Definition at line 1538 of file training_strategy.cpp.

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

Protected Attributes
PerformanceFunctional *	performance_functional_pointer

RandomSearch *	random_search_pointer

EvolutionaryAlgorithm *	evolutionary_algorithm_pointer

GradientDescent *	gradient_descent_pointer

ConjugateGradient *	conjugate_gradient_pointer

QuasiNewtonMethod *	quasi_Newton_method_pointer

LevenbergMarquardtAlgorithm *	Levenberg_Marquardt_algorithm_pointer

NewtonMethod *	Newton_method_pointer

InitializationType	initialization_type

MainType	main_type

RefinementType	refinement_type

bool	display

Classes

Public Types

Public Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation