OpenNN::TrainingAlgorithm Class Reference

#include <training_algorithm.h>

Inheritance diagram for OpenNN::TrainingAlgorithm:

Classes
struct	TrainingAlgorithmResults

Public Member Functions
	TrainingAlgorithm (void)
	TrainingAlgorithm (PerformanceFunctional *)
	TrainingAlgorithm (const tinyxml2::XMLDocument &)
virtual	~TrainingAlgorithm (void)
virtual TrainingAlgorithm &	operator= (const TrainingAlgorithm &)
virtual bool	operator== (const TrainingAlgorithm &) const
PerformanceFunctional *	get_performance_functional_pointer (void) const
bool	has_performance_functional (void) const
const bool &	get_display (void) const
const size_t &	get_display_period (void) const
const size_t &	get_save_period (void) const
const std::string &	get_neural_network_file_name (void) const
void	set (void)
void	set (PerformanceFunctional *)
virtual void	set_default (void)
virtual void	set_performance_functional_pointer (PerformanceFunctional *)
void	set_display (const bool &)
void	set_display_period (const size_t &)
void	set_save_period (const size_t &)
void	set_neural_network_file_name (const std::string &)
virtual void	check (void) const
virtual TrainingAlgorithmResults *	perform_training (void)=0
virtual std::string	write_training_algorithm_type (void) const
virtual std::string	to_string (void) const
void	print (void) const
virtual Matrix< std::string >	to_string_matrix (void) const
virtual tinyxml2::XMLDocument *	to_XML (void) const
virtual void	from_XML (const tinyxml2::XMLDocument &)
void	save (const std::string &) const
void	load (const std::string &)
virtual void	initialize_random (void)

Protected Attributes
PerformanceFunctional *	performance_functional_pointer
size_t	display_period
size_t	save_period
std::string	neural_network_file_name
bool	display

Detailed Description

This abstract class represents the concept of training algorithm for a neural network. Any derived class must implement the perform_training(void) method.

Definition at line 41 of file training_algorithm.h.

Constructor & Destructor Documentation

OpenNN::TrainingAlgorithm::TrainingAlgorithm ( void  )

explicit

Default constructor. It creates a training algorithm object not associated to any performance functional object.

Definition at line 27 of file training_algorithm.cpp.

OpenNN::TrainingAlgorithm::TrainingAlgorithm ( PerformanceFunctional *  new_performance_functional_pointer )

explicit

General constructor. It creates a training algorithm object associated to a performance functional object.

Parameters

new_performance_functional_pointer

Pointer to a performance functional object.

Definition at line 40 of file training_algorithm.cpp.

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

explicit

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

Definition at line 53 of file training_algorithm.cpp.

Member Function Documentation

void OpenNN::TrainingAlgorithm::check ( void  ) const

virtual

Performs a default checking for training algorithms. In particular, it checks that the performance functional pointer associated to the training algorithm is not NULL, and that the neural network associated to that performance functional is neither NULL. If that checkings are not hold, an exception is thrown.

Reimplemented in OpenNN::LevenbergMarquardtAlgorithm.

Definition at line 348 of file training_algorithm.cpp.

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

virtual

Loads a default training algorithm from a XML document.

Parameters

document

TinyXML document containing the performance term members.

Reimplemented in OpenNN::EvolutionaryAlgorithm, OpenNN::QuasiNewtonMethod, OpenNN::ConjugateGradient, OpenNN::NewtonMethod, OpenNN::LevenbergMarquardtAlgorithm, OpenNN::GradientDescent, and OpenNN::RandomSearch.

Definition at line 412 of file training_algorithm.cpp.

const bool & OpenNN::TrainingAlgorithm::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 158 of file training_algorithm.cpp.

PerformanceFunctional * OpenNN::TrainingAlgorithm::get_performance_functional_pointer

(

void

)

const

Returns a pointer to the performance functional object to which the training algorithm is associated.

Definition at line 114 of file training_algorithm.cpp.

bool OpenNN::TrainingAlgorithm::has_performance_functional

(

void

)

const

Returns true if this training algorithm object has an associated performance functional object, and false otherwise.

Definition at line 140 of file training_algorithm.cpp.

void OpenNN::TrainingAlgorithm::initialize_random ( void  )

virtual

Default random initialization for a training algorithm object. It just sets a random display value.

Reimplemented in OpenNN::EvolutionaryAlgorithm.

Definition at line 534 of file training_algorithm.cpp.

void OpenNN::TrainingAlgorithm::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 508 of file training_algorithm.cpp.

TrainingAlgorithm & OpenNN::TrainingAlgorithm::operator= ( const TrainingAlgorithm &  other_training_algorithm )

virtual

Assignment operator. It assigns to this object the members of an existing training algorithm object.

Parameters

other_training_algorithm

Training algorithm object to be assigned.

Definition at line 75 of file training_algorithm.cpp.

bool OpenNN::TrainingAlgorithm::operator== ( const TrainingAlgorithm &  other_training_algorithm ) const

virtual

Equal to operator.

Parameters

other_training_algorithm

Training algorithm object to be compared with.

Definition at line 93 of file training_algorithm.cpp.

void OpenNN::TrainingAlgorithm::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 492 of file training_algorithm.cpp.

void OpenNN::TrainingAlgorithm::set

(

void

)

Sets the performance functional pointer to NULL. It also sets the rest of members to their default values.

Definition at line 199 of file training_algorithm.cpp.

void OpenNN::TrainingAlgorithm::set

(

PerformanceFunctional *

new_performance_functional_pointer

)

Sets a new performance functional pointer. It also sets the rest of members to their default values.

Parameters

new_performance_functional_pointer

Pointer to a performance functional object.

Definition at line 213 of file training_algorithm.cpp.

void OpenNN::TrainingAlgorithm::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 239 of file training_algorithm.cpp.

void OpenNN::TrainingAlgorithm::set_display_period

(

const size_t &

new_display_period

)

Sets a new number of iterations between the training showing progress.

Parameters

new_display_period

Number of iterations between the training showing progress.

Definition at line 251 of file training_algorithm.cpp.

void OpenNN::TrainingAlgorithm::set_neural_network_file_name

(

const std::string &

new_neural_network_file_name

)

Sets a new file name where the neural network will be saved.

Parameters

new_neural_network_file_name

File name for the neural network object.

Definition at line 309 of file training_algorithm.cpp.

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

virtual

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

Parameters

new_performance_functional_pointer

Pointer to a performance functional object.

Reimplemented in OpenNN::QuasiNewtonMethod, OpenNN::ConjugateGradient, OpenNN::NewtonMethod, and OpenNN::GradientDescent.

Definition at line 226 of file training_algorithm.cpp.

void OpenNN::TrainingAlgorithm::set_save_period

(

const size_t &

new_save_period

)

Sets a new number of iterations between the training saving progress.

Parameters

new_save_period

Number of iterations between the training saving progress.

Definition at line 280 of file training_algorithm.cpp.

Matrix< std::string > OpenNN::TrainingAlgorithm::to_string_matrix ( void  ) const

virtual

Returns a default (empty) string matrix containing the members of the training algorithm object.

Reimplemented in OpenNN::EvolutionaryAlgorithm, OpenNN::QuasiNewtonMethod, OpenNN::ConjugateGradient, OpenNN::NewtonMethod, OpenNN::LevenbergMarquardtAlgorithm, OpenNN::GradientDescent, and OpenNN::RandomSearch.

Definition at line 469 of file training_algorithm.cpp.

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

virtual

Serializes a default training algorithm object into a XML document of the TinyXML library. See the OpenNN manual for more information about the format of this document.

Reimplemented in OpenNN::EvolutionaryAlgorithm, OpenNN::QuasiNewtonMethod, OpenNN::ConjugateGradient, OpenNN::NewtonMethod, OpenNN::LevenbergMarquardtAlgorithm, OpenNN::GradientDescent, and OpenNN::RandomSearch.

Definition at line 379 of file training_algorithm.cpp.

---

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

• training_algorithm.h
• training_algorithm.cpp