This class represents the normalized squared error term. More...

#include <normalized_squared_error.h>

Inheritance diagram for NormalizedSquaredError:

Public Member Functions
	NormalizedSquaredError (NeuralNetwork , DataSet )

	NormalizedSquaredError ()

virtual	~NormalizedSquaredError ()
	Destructor. More...

type	get_normalization_coefficient () const
	Returns the normalization coefficient. More...

type	get_selection_normalization_coefficient () const
	Returns the selection normalization coefficient. More...

void	set_normalization_coefficient ()

void	set_normalization_coefficient (const type &)

void	set_time_series_normalization_coefficient ()

void	set_selection_normalization_coefficient ()

void	set_selection_normalization_coefficient (const type &)

void	set_default ()
	Sets the default values. More...

void	set_data_set_pointer (DataSet *new_data_set_pointer)
	set_data_set_pointer More...

type	calculate_normalization_coefficient (const Tensor< type, 2 > &, const Tensor< type, 1 > &) const

type	calculate_time_series_normalization_coefficient (const Tensor< type, 2 > &, const Tensor< type, 2 > &) const

void	calculate_error (const DataSetBatch &, const NeuralNetworkForwardPropagation &, LossIndexBackPropagation &) const
	NormalizedSquaredError::calculate_error. More...

void	calculate_output_delta (const DataSetBatch &, NeuralNetworkForwardPropagation &, LossIndexBackPropagation &) const

void	calculate_error_lm (const DataSetBatch &, const NeuralNetworkForwardPropagation &, LossIndexBackPropagationLM &) const

void	calculate_output_delta_lm (const DataSetBatch &, NeuralNetworkForwardPropagation &, LossIndexBackPropagationLM &) const

void	calculate_error_gradient_lm (const DataSetBatch &, LossIndexBackPropagationLM &) const

void	calculate_error_hessian_lm (const DataSetBatch &, LossIndexBackPropagationLM &) const

string	get_error_type () const
	Returns a string with the name of the normalized squared error loss type, "NORMALIZED_SQUARED_ERROR". More...

string	get_error_type_text () const
	Returns a string with the name of the normalized squared error loss type in text format. More...

void	from_XML (const tinyxml2::XMLDocument &)

void	write_XML (tinyxml2::XMLPrinter &) const

Public Member Functions inherited from LossIndex
	LossIndex ()

	LossIndex (NeuralNetwork , DataSet )

virtual	~LossIndex ()
	Destructor. More...

NeuralNetwork *	get_neural_network_pointer () const
	Returns a pointer to the neural network object associated to the error term. More...

DataSet *	get_data_set_pointer () const
	Returns a pointer to the data set object associated to the error term. More...

const type &	get_regularization_weight () const
	Returns regularization weight. More...

const bool &	get_display () const

bool	has_neural_network () const

bool	has_data_set () const

RegularizationMethod	get_regularization_method () const
	Returns the regularization method. More...

void	set ()

void	set (NeuralNetwork *)

void	set (DataSet *)

void	set (NeuralNetwork , DataSet )

void	set (const LossIndex &)

void	set_threads_number (const int &)

void	set_neural_network_pointer (NeuralNetwork *)

void	set_default ()
	Sets the members of the error term to their default values: More...

void	set_regularization_method (const RegularizationMethod &)

void	set_regularization_method (const string &)

void	set_regularization_weight (const type &)

void	set_display (const bool &)

bool	has_selection () const
	Returns true if there are selection samples and false otherwise. More...

type	calculate_eta () const

type	calculate_h (const type &) const

Tensor< type, 1 >	calculate_gradient_numerical_differentiation ()

Tensor< type, 2 >	calculate_jacobian_numerical_differentiation ()

void	calculate_errors (const DataSetBatch &, const NeuralNetworkForwardPropagation &, LossIndexBackPropagation &) const

void	calculate_layers_delta (const DataSetBatch &, NeuralNetworkForwardPropagation &, LossIndexBackPropagation &) const

void	calculate_error_gradient (const DataSetBatch &, const NeuralNetworkForwardPropagation &, LossIndexBackPropagation &) const

void	back_propagate (const DataSetBatch &, NeuralNetworkForwardPropagation &, LossIndexBackPropagation &) const

void	calculate_errors_lm (const DataSetBatch &, const NeuralNetworkForwardPropagation &, LossIndexBackPropagationLM &) const

virtual void	calculate_squared_errors_lm (const DataSetBatch &, const NeuralNetworkForwardPropagation &, LossIndexBackPropagationLM &) const

void	calculate_layers_delta_lm (const DataSetBatch &, NeuralNetworkForwardPropagation &, LossIndexBackPropagationLM &) const

void	calculate_squared_errors_jacobian_lm (const DataSetBatch &, NeuralNetworkForwardPropagation &, LossIndexBackPropagationLM &) const

void	back_propagate_lm (const DataSetBatch &, NeuralNetworkForwardPropagation &, LossIndexBackPropagationLM &) const

type	calculate_regularization (const Tensor< type, 1 > &) const

void	calculate_regularization_gradient (const Tensor< type, 1 > &, Tensor< type, 1 > &) const

void	calculate_regularization_hessian (const Tensor< type, 1 > &, Tensor< type, 2 > &) const

void	from_XML (const tinyxml2::XMLDocument &)

void	regularization_from_XML (const tinyxml2::XMLDocument &)

void	write_regularization_XML (tinyxml2::XMLPrinter &) const

string	write_regularization_method () const

void	check () const

Private Attributes
type	normalization_coefficient = type(NAN)
	Coefficient of normalization for the calculation of the training error. More...

type	selection_normalization_coefficient = type(NAN)

Additional Inherited Members
Public Types inherited from LossIndex
enum class	RegularizationMethod { L1 , L2 , NoRegularization }
	Enumeration of available regularization methods. More...

Protected Attributes inherited from LossIndex
NonBlockingThreadPool *	non_blocking_thread_pool = nullptr

ThreadPoolDevice *	thread_pool_device = nullptr

NeuralNetwork *	neural_network_pointer = nullptr
	Pointer to a neural network object. More...

DataSet *	data_set_pointer = nullptr
	Pointer to a data set object. More...

RegularizationMethod	regularization_method = RegularizationMethod::L2
	Pointer to a regularization method object. More...

type	regularization_weight = static_cast<type>(0.01)
	Regularization weight value. 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 >	A_B = {IndexPair<Index>(1, 0)}

const Eigen::array< IndexPair< Index >, 2 >	SSE = {IndexPair<Index>(0, 0), IndexPair<Index>(1, 1)}

const Eigen::array< int, 1 >	rows_sum = {Eigen::array<int, 1>({1})}

Detailed Description

This class represents the normalized squared error term.

This error term is used in data modeling problems. If it has a value of unity then the neural network is predicting the data "in the mean", A value of zero means perfect prediction of data.

Definition at line 37 of file normalized_squared_error.h.

Constructor & Destructor Documentation

◆ NormalizedSquaredError() [1/2]

NormalizedSquaredError	(	NeuralNetwork *	new_neural_network_pointer,
		DataSet *	new_data_set_pointer
	)

explicit

Neural network and data set constructor. It creates a normalized squared error term associated to a neural network and measured 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.
new_data_set_pointer	Pointer to a data set object.

Definition at line 31 of file normalized_squared_error.cpp.

◆ NormalizedSquaredError() [2/2]

NormalizedSquaredError ( )

explicit

Default constructor. It creates a normalized squared error term object not associated to any neural network and not measured on any data set. It also initializes all the rest of class members to their default values.

Definition at line 19 of file normalized_squared_error.cpp.

◆ ~NormalizedSquaredError()

~NormalizedSquaredError ( )

virtual

Destructor.

Definition at line 40 of file normalized_squared_error.cpp.

Member Function Documentation

◆ calculate_error()

void calculate_error	(	const DataSetBatch &	batch,
		const NeuralNetworkForwardPropagation &	,
		LossIndexBackPropagation &	back_propagation
	)		const

virtual

NormalizedSquaredError::calculate_error.

Parameters

batch
forward_propagation
back_propagation

Implements LossIndex.

Definition at line 282 of file normalized_squared_error.cpp.

◆ calculate_error_gradient_lm()

void calculate_error_gradient_lm	(	const DataSetBatch &	batch,
		LossIndexBackPropagationLM &	loss_index_back_propagation_lm
	)		const

virtual

Reimplemented from LossIndex.

Definition at line 465 of file normalized_squared_error.cpp.

◆ calculate_error_hessian_lm()

void calculate_error_hessian_lm	(	const DataSetBatch &	batch,
		LossIndexBackPropagationLM &	loss_index_back_propagation_lm
	)		const

virtual

Reimplemented from LossIndex.

Definition at line 480 of file normalized_squared_error.cpp.

◆ calculate_error_lm()

void calculate_error_lm	(	const DataSetBatch &	batch,
		const NeuralNetworkForwardPropagation &	,
		LossIndexBackPropagationLM &	back_propagation
	)		const

virtual

Reimplemented from LossIndex.

Definition at line 314 of file normalized_squared_error.cpp.

◆ calculate_normalization_coefficient()

type calculate_normalization_coefficient	(	const Tensor< type, 2 > &	targets,
		const Tensor< type, 1 > &	targets_mean
	)		const

Returns the normalization coefficient to be used for the loss of the error. This is measured on the training samples of the data set.

Parameters

targets	Matrix with the targets values from data_set.
targets_mean	Vector with the means of the given targets.

Definition at line 238 of file normalized_squared_error.cpp.

◆ calculate_output_delta()

void calculate_output_delta	(	const DataSetBatch &	batch,
		NeuralNetworkForwardPropagation &	,
		LossIndexBackPropagation &	back_propagation
	)		const

virtual

Implements LossIndex.

Definition at line 345 of file normalized_squared_error.cpp.

◆ calculate_output_delta_lm()

void calculate_output_delta_lm	(	const DataSetBatch &	,
		NeuralNetworkForwardPropagation &	,
		LossIndexBackPropagationLM &	loss_index_back_propagation
	)		const

virtual

Reimplemented from LossIndex.

Definition at line 410 of file normalized_squared_error.cpp.

◆ calculate_time_series_normalization_coefficient()

type calculate_time_series_normalization_coefficient	(	const Tensor< type, 2 > &	targets_t_1,
		const Tensor< type, 2 > &	targets_t
	)		const

Definition at line 133 of file normalized_squared_error.cpp.

◆ from_XML()

void from_XML ( const tinyxml2::XMLDocument & document )

Loads a root mean squared error object from a XML document.

Parameters

document Pointer to a TinyXML document with the object data.

Definition at line 533 of file normalized_squared_error.cpp.

◆ get_error_type()

string get_error_type ( ) const

virtual

Returns a string with the name of the normalized squared error loss type, "NORMALIZED_SQUARED_ERROR".

Reimplemented from LossIndex.

Definition at line 503 of file normalized_squared_error.cpp.

◆ get_error_type_text()

string get_error_type_text ( ) const

virtual

Returns a string with the name of the normalized squared error loss type in text format.

Reimplemented from LossIndex.

Definition at line 511 of file normalized_squared_error.cpp.

◆ get_normalization_coefficient()

type get_normalization_coefficient ( ) const

Returns the normalization coefficient.

Definition at line 47 of file normalized_squared_error.cpp.

◆ get_selection_normalization_coefficient()

type get_selection_normalization_coefficient ( ) const

Returns the selection normalization coefficient.

Definition at line 55 of file normalized_squared_error.cpp.

◆ set_data_set_pointer()

void set_data_set_pointer ( DataSet * new_data_set_pointer )

virtual

set_data_set_pointer

Parameters

new_data_set_pointer

Reimplemented from LossIndex.

Definition at line 65 of file normalized_squared_error.cpp.

◆ set_default()

void set_default ( )

Sets the default values.

Definition at line 218 of file normalized_squared_error.cpp.

◆ set_normalization_coefficient() [1/2]

void set_normalization_coefficient ( )

virtual

Sets the normalization coefficient from training samples. This method calculates the normalization coefficient of the data_set.

Reimplemented from LossIndex.

Definition at line 83 of file normalized_squared_error.cpp.

◆ set_normalization_coefficient() [2/2]

void set_normalization_coefficient ( const type & new_normalization_coefficient )

Sets the normalization coefficient.

Parameters

new_normalization_coefficient New normalization coefficient to be set.

Definition at line 178 of file normalized_squared_error.cpp.

◆ set_selection_normalization_coefficient() [1/2]

void set_selection_normalization_coefficient ( )

Sets the normalization coefficient from selection samples. This method calculates the normalization coefficient of the data_set.

Definition at line 187 of file normalized_squared_error.cpp.

◆ set_selection_normalization_coefficient() [2/2]

void set_selection_normalization_coefficient ( const type & new_selection_normalization_coefficient )

Sets the normalization coefficient from selection samples.

Parameters

new_normalization_coefficient New normalization coefficient to be set.

Definition at line 210 of file normalized_squared_error.cpp.

◆ set_time_series_normalization_coefficient()

void set_time_series_normalization_coefficient ( )

Todo:: What is targets_t1 ???

Definition at line 101 of file normalized_squared_error.cpp.

◆ write_XML()

void write_XML ( tinyxml2::XMLPrinter & file_stream ) const

virtual

Serializes the cross entropy error 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 LossIndex.

Definition at line 520 of file normalized_squared_error.cpp.

Member Data Documentation

◆ normalization_coefficient

type normalization_coefficient = type(NAN)

private

Coefficient of normalization for the calculation of the training error.

Definition at line 116 of file normalized_squared_error.h.

◆ selection_normalization_coefficient

type selection_normalization_coefficient = type(NAN)

private

Definition at line 118 of file normalized_squared_error.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

◆ NormalizedSquaredError() [1/2]

◆ NormalizedSquaredError() [2/2]

◆ ~NormalizedSquaredError()

Member Function Documentation

◆ calculate_error()

◆ calculate_error_gradient_lm()

◆ calculate_error_hessian_lm()

◆ calculate_error_lm()

◆ calculate_normalization_coefficient()

◆ calculate_output_delta()

◆ calculate_output_delta_lm()

◆ calculate_time_series_normalization_coefficient()

◆ from_XML()

◆ get_error_type()

◆ get_error_type_text()

◆ get_normalization_coefficient()

◆ get_selection_normalization_coefficient()

◆ set_data_set_pointer()

◆ set_default()

◆ set_normalization_coefficient() [1/2]

◆ set_normalization_coefficient() [2/2]

◆ set_selection_normalization_coefficient() [1/2]

◆ set_selection_normalization_coefficient() [2/2]

◆ set_time_series_normalization_coefficient()

◆ write_XML()

Member Data Documentation

◆ normalization_coefficient

◆ selection_normalization_coefficient