#include <adaptive_moment_estimation.h>

Inheritance diagram for AdaptiveMomentEstimation:

Public Member Functions
	AdaptiveMomentEstimation ()

	AdaptiveMomentEstimation (LossIndex *)

virtual	~AdaptiveMomentEstimation ()
	Destructor. More...

const type &	get_initial_learning_rate () const
	Returns the initial learning rate. More...

const type &	get_beta_1 () const
	Returns beta 1. More...

const type &	get_beta_2 () const
	Returns beta 2. More...

const type &	get_epsilon () const
	Returns epsilon. More...

const type &	get_loss_goal () const

const type &	get_maximum_time () const
	Returns the maximum training time. More...

void	set_loss_index_pointer (LossIndex *)

void	set_batch_samples_number (const Index &new_batch_samples_number)
	Set number of samples in each batch. Default 1000. More...

void	set_default ()
	Sets the members of the optimization algorithm object to their default values. More...

Index	get_batch_samples_number () const

void	set_initial_learning_rate (const type &)

void	set_beta_1 (const type &)

void	set_beta_2 (const type &)

void	set_epsilon (const type &)

void	set_maximum_epochs_number (const Index &)

void	set_loss_goal (const type &)

void	set_maximum_time (const type &)

TrainingResults	perform_training ()

string	write_optimization_algorithm_type () const
	Return the algorithm optimum for your model. More...

Tensor< string, 2 >	to_string_matrix () const
	Writes as matrix of strings the most representative atributes. More...

void	from_XML (const tinyxml2::XMLDocument &)

void	write_XML (tinyxml2::XMLPrinter &) const

void	update_parameters (LossIndexBackPropagation &, AdaptiveMomentEstimationData &)
	Update iteration parameters. More...

Public Member Functions inherited from OptimizationAlgorithm
	OptimizationAlgorithm ()

	OptimizationAlgorithm (LossIndex *)

virtual	~OptimizationAlgorithm ()
	Destructor. More...

LossIndex *	get_loss_index_pointer () const

string	get_hardware_use () const
	Hardware use. More...

void	set_hardware_use (const string &)
	Set hardware to use. Default: Multi-core. More...

bool	has_loss_index () const

const bool &	get_display () const

const Index &	get_display_period () const
	Returns the number of iterations between the training showing progress. More...

const Index &	get_save_period () const
	Returns the number of iterations between the training saving progress. More...

const string &	get_neural_network_file_name () const
	Returns the file name where the neural network will be saved. More...

const string	write_time (const type &) const
	Writes the time from seconds in format HH:mm:ss. More...

void	set ()

virtual void	set_threads_number (const int &)

virtual void	set_display (const bool &)

void	set_display_period (const Index &)

void	set_save_period (const Index &)

void	set_neural_network_file_name (const string &)

virtual void	check () const

virtual void	print () const
	Prints to the screen the XML-type representation of the optimization algorithm object. More...

void	save (const string &) const

void	load (const string &)

Private Attributes
type	initial_learning_rate = static_cast<type>(0.001)
	Initial learning rate. More...

type	initial_decay = type(0)
	Learning rate decay over each update. More...

type	beta_1 = static_cast<type>(0.9)
	Exponential decay over gradient estimates. More...

type	beta_2 = static_cast<type>(0.999)
	Exponential decay over square gradient estimates. More...

type	epsilon =static_cast<type>(1.e-7)
	Small number to prevent any division by zero. More...

type	training_loss_goal = type(0)
	Goal value for the loss. It is used as a stopping criterion. More...

Index	maximum_epochs_number = 10000
	Maximum epochs number. More...

Index	maximum_selection_failures = numeric_limits<Index>::max()
	Maximum number of times when selection error increases. More...

type	maximum_time = type(3600)
	Maximum training time. It is used as a stopping criterion. More...

Index	batch_samples_number = 1000
	Training and selection batch size. More...

Additional Inherited Members
Public Types inherited from OptimizationAlgorithm
enum class	StoppingCondition { MinimumLossDecrease , LossGoal , MaximumSelectionErrorIncreases , MaximumEpochsNumber , MaximumTime }
	Enumeration of all possibles condition of stop for the algorithms. More...

Protected Attributes inherited from OptimizationAlgorithm
NonBlockingThreadPool *	non_blocking_thread_pool = nullptr

ThreadPoolDevice *	thread_pool_device

LossIndex *	loss_index_pointer = nullptr
	Pointer to a loss index for a neural network object. More...

Index	epochs_number = 10000
	Number of training epochs in the neural network. More...

string	hardware_use = "Multi-core"
	Hardware use. More...

Index	display_period = 10
	Number of iterations between the training showing progress. More...

Index	save_period = numeric_limits<Index>::max()
	Number of iterations between the training saving progress. More...

string	neural_network_file_name = "neural_network.xml"
	Path where the neural network is saved. More...

bool	display = true
	Display messages to screen. More...

const Eigen::array< IndexPair< Index >, 1 >	AT_B = {IndexPair<Index>(0, 0)}

const Eigen::array< IndexPair< Index >, 1 >	product_vector_matrix = {IndexPair<Index>(0, 1)}

const Eigen::array< IndexPair< Index >, 1 >	A_B = {IndexPair<Index>(1, 0)}

Detailed Description

This concrete class represents the adaptive moment estimation (Adam) training algorithm, based on adaptive estimates of lower-order moments. For more information visit:

[1] C. Barranquero "High performance optimization algorithms for neural networks." https://www.opennn.net/files/high_performance_optimization_algorithms_for_neural_networks.pdf .

[2] D. P. Kingma and J. L. Ba, "Adam: A Method for Stochastic Optimization." arXiv preprint arXiv:1412.6980v8 (2014).

Definition at line 52 of file adaptive_moment_estimation.h.

Constructor & Destructor Documentation

◆ AdaptiveMomentEstimation() [1/2]

AdaptiveMomentEstimation ( )

explicit

Default constructor. It creates a adaptive moment estimation optimization algorithm not associated to any loss index object. It also initializes the class members to their default values.

Definition at line 18 of file adaptive_moment_estimation.cpp.

◆ AdaptiveMomentEstimation() [2/2]

AdaptiveMomentEstimation ( LossIndex * new_loss_index_pointer )

explicit

Loss index constructor. It creates a adaptive moment estimation optimization algorithm associated to a loss index. It also initializes the class members to their default values.

Parameters

new_loss_index_pointer Pointer to a loss index object.

Definition at line 30 of file adaptive_moment_estimation.cpp.

◆ ~AdaptiveMomentEstimation()

~AdaptiveMomentEstimation ( )

virtual

Destructor.

Definition at line 39 of file adaptive_moment_estimation.cpp.

Member Function Documentation

◆ from_XML()

void from_XML ( const tinyxml2::XMLDocument & document )

virtual

Loads a default optimization algorithm from a XML document.

Parameters

document TinyXML document containing the error term members.

Reimplemented from OptimizationAlgorithm.

Definition at line 595 of file adaptive_moment_estimation.cpp.

◆ get_batch_samples_number()

Index get_batch_samples_number ( ) const

Definition at line 720 of file adaptive_moment_estimation.cpp.

◆ get_beta_1()

const type & get_beta_1 ( ) const

Returns beta 1.

Definition at line 54 of file adaptive_moment_estimation.cpp.

◆ get_beta_2()

const type & get_beta_2 ( ) const

Returns beta 2.

Definition at line 62 of file adaptive_moment_estimation.cpp.

◆ get_epsilon()

const type & get_epsilon ( ) const

Returns epsilon.

Definition at line 70 of file adaptive_moment_estimation.cpp.

◆ get_initial_learning_rate()

const type & get_initial_learning_rate ( ) const

Returns the initial learning rate.

Definition at line 46 of file adaptive_moment_estimation.cpp.

◆ get_loss_goal()

const type & get_loss_goal ( ) const

Returns the goal value for the loss. This is used as a stopping criterion when training a neural network

Definition at line 79 of file adaptive_moment_estimation.cpp.

◆ get_maximum_time()

const type & get_maximum_time ( ) const

Returns the maximum training time.

Definition at line 87 of file adaptive_moment_estimation.cpp.

◆ perform_training()

TrainingResults perform_training ( )

virtual

Trains a neural network with an associated loss index, according to the gradient descent method. Training occurs according to the training parameters and stopping criteria. It returns a results structure with the history and the final values of the reserved variables.

Implements OptimizationAlgorithm.

Definition at line 206 of file adaptive_moment_estimation.cpp.

◆ set_batch_samples_number()

void set_batch_samples_number ( const Index & new_batch_samples_number )

Set number of samples in each batch. Default 1000.

Definition at line 708 of file adaptive_moment_estimation.cpp.

◆ set_beta_1()

void set_beta_1 ( const type & new_beta_1 )

Sets beta 1 generally close to 1.

Parameters

new_beta_1.

Definition at line 115 of file adaptive_moment_estimation.cpp.

◆ set_beta_2()

void set_beta_2 ( const type & new_beta_2 )

Sets beta 2 generally close to 1.

Parameters

new_beta_2.

Definition at line 124 of file adaptive_moment_estimation.cpp.

◆ set_default()

void set_default ( )

virtual

Sets the members of the optimization algorithm object to their default values.

Reimplemented from OptimizationAlgorithm.

Definition at line 714 of file adaptive_moment_estimation.cpp.

◆ set_epsilon()

void set_epsilon ( const type & new_epsilon )

Sets epsilon.

Parameters

epsilon.

Definition at line 133 of file adaptive_moment_estimation.cpp.

◆ set_initial_learning_rate()

void set_initial_learning_rate ( const type & new_learning_rate )

Sets a new learning rate.

Parameters

new_learning_rate.

Definition at line 106 of file adaptive_moment_estimation.cpp.

◆ set_loss_goal()

void set_loss_goal ( const type & new_loss_goal )

Sets a new goal value for the loss. This is used as a stopping criterion when training a neural network

Parameters

new_loss_goal Goal value for the loss.

Definition at line 169 of file adaptive_moment_estimation.cpp.

◆ set_loss_index_pointer()

void set_loss_index_pointer ( LossIndex * new_loss_index_pointer )

virtual

Sets a pointer to a loss index object to be associated to the gradient descent object. It also sets that loss index to the learning rate algorithm.

Parameters

new_loss_index_pointer Pointer to a loss index object.

Reimplemented from OptimizationAlgorithm.

Definition at line 97 of file adaptive_moment_estimation.cpp.

◆ set_maximum_epochs_number()

void set_maximum_epochs_number ( const Index & new_maximum_epochs_number )

Set the a new maximum for the epochs number.

Parameters

new_maximum_epochs number New maximum epochs number.

Definition at line 142 of file adaptive_moment_estimation.cpp.

◆ set_maximum_time()

void set_maximum_time ( const type & new_maximum_time )

Sets a new maximum training time.

Parameters

new_maximum_time Maximum training time.

Definition at line 178 of file adaptive_moment_estimation.cpp.

◆ to_string_matrix()

Tensor< string, 2 > to_string_matrix ( ) const

virtual

Writes as matrix of strings the most representative atributes.

Reimplemented from OptimizationAlgorithm.

Definition at line 472 of file adaptive_moment_estimation.cpp.

◆ update_parameters()

void update_parameters	(	LossIndexBackPropagation &	back_propagation,
		AdaptiveMomentEstimationData &	optimization_data
	)

Update iteration parameters.

Definition at line 728 of file adaptive_moment_estimation.cpp.

◆ write_optimization_algorithm_type()

string write_optimization_algorithm_type ( ) const

virtual

Return the algorithm optimum for your model.

Reimplemented from OptimizationAlgorithm.

Definition at line 464 of file adaptive_moment_estimation.cpp.

◆ write_XML()

void write_XML ( tinyxml2::XMLPrinter & file_stream ) const

virtual

Serializes the gradient descent object into a XML document of the TinyXML library without keep the DOM tree in memory. See the OpenNN manual for more information about the format of this document.

Reimplemented from OptimizationAlgorithm.

Definition at line 528 of file adaptive_moment_estimation.cpp.

Member Data Documentation

◆ batch_samples_number

Index batch_samples_number = 1000

private

Training and selection batch size.

Definition at line 168 of file adaptive_moment_estimation.h.

◆ beta_1

type beta_1 = static_cast<type>(0.9)

private

Exponential decay over gradient estimates.

Definition at line 138 of file adaptive_moment_estimation.h.

◆ beta_2

type beta_2 = static_cast<type>(0.999)

private

Exponential decay over square gradient estimates.

Definition at line 142 of file adaptive_moment_estimation.h.

◆ epsilon

type epsilon =static_cast<type>(1.e-7)

private

Small number to prevent any division by zero.

Definition at line 146 of file adaptive_moment_estimation.h.

◆ initial_decay

type initial_decay = type(0)

private

Learning rate decay over each update.

Definition at line 134 of file adaptive_moment_estimation.h.

◆ initial_learning_rate

type initial_learning_rate = static_cast<type>(0.001)

private

Initial learning rate.

Definition at line 130 of file adaptive_moment_estimation.h.

◆ maximum_epochs_number

Index maximum_epochs_number = 10000

private

Maximum epochs number.

Definition at line 156 of file adaptive_moment_estimation.h.

◆ maximum_selection_failures

Index maximum_selection_failures = numeric_limits<Index>::max()

private

Maximum number of times when selection error increases.

Definition at line 160 of file adaptive_moment_estimation.h.

◆ maximum_time

type maximum_time = type(3600)

private

Maximum training time. It is used as a stopping criterion.

Definition at line 164 of file adaptive_moment_estimation.h.

◆ training_loss_goal

type training_loss_goal = type(0)

private

Goal value for the loss. It is used as a stopping criterion.

Definition at line 152 of file adaptive_moment_estimation.h.

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

Public Member Functions

Private Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ AdaptiveMomentEstimation() [1/2]

◆ AdaptiveMomentEstimation() [2/2]

◆ ~AdaptiveMomentEstimation()

Member Function Documentation

◆ from_XML()

◆ get_batch_samples_number()

◆ get_beta_1()

◆ get_beta_2()

◆ get_epsilon()

◆ get_initial_learning_rate()

◆ get_loss_goal()

◆ get_maximum_time()

◆ perform_training()

◆ set_batch_samples_number()

◆ set_beta_1()

◆ set_beta_2()

◆ set_default()

◆ set_epsilon()

◆ set_initial_learning_rate()

◆ set_loss_goal()

◆ set_loss_index_pointer()

◆ set_maximum_epochs_number()

◆ set_maximum_time()

◆ to_string_matrix()

◆ update_parameters()

◆ write_optimization_algorithm_type()

◆ write_XML()

Member Data Documentation

◆ batch_samples_number

◆ beta_1

◆ beta_2

◆ epsilon

◆ initial_decay

◆ initial_learning_rate

◆ maximum_epochs_number

◆ maximum_selection_failures

◆ maximum_time

◆ training_loss_goal