Transfer Object (DTO) for neural network training set. More...

Inheritance diagram for IG.Num.NeuralTrainingParametersDto:

Collaboration diagram for IG.Num.NeuralTrainingParametersDto:

Public Member Functions
override NeuralTrainingParameters	CreateObject ()
	Creates and returns a new object of the corresponding type. More...

Public Attributes
double	LearningRate
	Learning rate. More...

double	Momentum
	Momentum. Specifies how much changes of weight in the previous iterations affect changes in the current iterations. More...

double	SigmoidAlphaValue
	Sigmoid alpha value (used in networks with sigmoid activation functions). More...

int	InputLength
	Gets or sets the number of input neurons. More...

int	OutputLength
	Gets or sets the number of output neurons. More...

double	InputBoundSafetyFactor

double	OutputBoundSafetyFactor

int	MaxEpochs
	Maximal number of epochs performed in the training procedure. More...

int	EpochsInBundle
	Number of epochs in bundle (i.e. number of epochs performed at once, without any checks or output operations between). More...

VectorDtoBase	InputRange
	Range from actual inputs. More...

VectorDtoBase	OutputRange
	Range from actual outputs. More...

VectorDtoBase	ToleranceRms
	Tolerance over RMS error of outputs over training points. Training will continue until error becomes below tolerance or until maximal number of epochs is reached. If less or equal than 0 then this tolerance is not taken into account. More...

VectorDtoBase	ToleranceRmsRelativeToRange
	Relative tolerances on RMS errors of outputs over training points, relative to the correspoinding ranges of output data. More...

double	ToleranceRmsRelativeToRangeScalar = NeuralTrainingParameters.DefaultToleranceRmsRelativeToRangeScalar
	Scalar through which all components of the Relative tolerances on RMS errors of outputs can be set to the same value. More...

VectorDtoBase	ToleranceMax
	Tolerance on maximal error of outputs over training points. Training will continue until error becomes below tolerance or until maximal number of epochs is reached. If less or equal than 0 then this tolerance is not taken into account. More...

VectorDtoBase	ToleranceMaxRelativeToRange
	Relative tolerances on max. abs. errors of outputs over training points, relative to the correspoinding ranges of output data. More...

double	ToleranceMaxRelativeToRangeScalar = NeuralTrainingParameters.DefaultToleranceMaxRelativeToRangeScalar
	Scalar through which all components of the Relative tolerances on max. abs. errors of outputs can be set to the same value. More...

int	NumHiddenLayers
	Number of Hideden layers. More...

int[]	NumHidenNeurons
	Numbers of neurons in each hidden layer. More...

bool	IsNetworkTrained
	Whether the network is trained (and results exist). More...

VectorDtoBase	ErrorsTrainingRms
	RMS errors calculated on training data. More...

VectorDtoBase[]	ErrorsTrainingRmsTable
	Convergence Table of RMS errors calculated on training data. More...

VectorDtoBase	ErrorsTrainingMax
	Maximal errors calculated on training data. More...

VectorDtoBase[]	ErrorsTrainingMaxTable
	Convergence Table of Maximal errors calculated on training data. More...

VectorDtoBase	ErrorsTrainingMeanAbs
	Mean absolute errors calculated on training data. More...

VectorDtoBase	ErrorsVerificationRms
	RMS errors calculated on verification data. More...

VectorDtoBase[]	ErrorsVerificationRmsTable
	Convergence Table of RMS errors calculated on verification data. More...

VectorDtoBase	ErrorsVerificationMax
	Maximal errors calculated on verification data. More...

VectorDtoBase[]	ErrorsVerificationMaxTable
	Convergence Table of Maximal errors calculated on verification data. More...

VectorDtoBase	ErrorsVerificationMeanAbs
	Maximal errors calculated on training data. More...

List< VectorDtoBase >	ErrorsRmsList

int	NumEpochs
	Number of epochs actually spent at training. More...

double	TrainingTime
	Time spent for training. More...

double	TrainingCpuTime
	CPU time spent for training. More...

int[]	EpochNumbers
	List of epoch numbers at which convergence data was sampled. More...

double[]	EpochErrorsRms
	List of sampled RMS errors corresponding to epoch numbers from EpochNumbers. More...

double[]	EpochErrorsAbs
	List of sampled absolute errors corresponding to epoch numbers from EpochNumbers. More...

Protected Member Functions
override void	CopyFromPlain (NeuralTrainingParameters trainingParameters)
	Copies the specified training parameters to the current DTO. More...

override void	CopyToPlain (ref NeuralTrainingParameters trainingParameters)
	Copies contents of the current DTO to the specified training parameters object. More...

Protected Member Functions inherited from IG.Lib.SerializationDto< NeuralTrainingParameters >
	SerializationDto ()

Additional Inherited Members
Static Public Member Functions inherited from IG.Lib.SerializationDto< NeuralTrainingParameters >
static ObjectType	CopyToObjectReturned< DtoType, ObjectType > (DtoType dto, ObjectType obj)
	Replacement for CopyToObject for cases where object can not be passed by reference. The returned object must be assigned to object (property, list element, etc.) to which object state is copied. More...

static void	CopyToObject< DtoType, ObjectType > (DtoType dto, ref ObjectType obj)
	Copies object state form the specified DTO (data transfer object) to the specified object. More...

static DtoType	CopyFromObjectReturned< DtoType, ObjectType > (ObjectType obj, DtoType dto)
	Replacement for CopyFromObject for cases where object can not be passed by reference. The returned object must be assigned to object (property, list element, etc.) to which object state is copied. More...

static void	CopyFromObject< DtoType, ObjectType > (ObjectType obj, ref DtoType dto)
	Copies object state form the specified object to the corresponding DTO (data transfer object). More...

static ObjectType[]	CopyArrayToObjectReturned< DtoType, ObjectType > (DtoType[] tabDto, ObjectType[] tabObj)
	Replacement for CopyArrayToObject for cases where object can not be passed by reference. The returned object must be assigned to object (property, list element, etc.) to which data is copied. More...

static void	CopyArrayToObject< DtoType, ObjectType > (DtoType[] tabDto, ref ObjectType[] tabObj)
	Copies array of DTOs (Data Transfer Objects) to an array of appropriate objects. More...

static DtoType[]	CopyArrayFromObjectReturned< DtoType, ObjectType > (ObjectType[] tabObj, DtoType[] tabDto)
	Replacement for CopyArrayFromObject for cases where object can not be passed by reference. The returned object must be assigned to object (property, list element, etc.) to which data is copied. More...

static void	CopyArrayFromObject< DtoType, ObjectType > (ObjectType[] tabObj, ref DtoType[] tabDto)
	Copies array of objects to an array of DTOs. More...

static List< ObjectType >	CopyListToObjectReturned< DtoType, ObjectType > (DtoType[] tabDto, List< ObjectType > listObj)
	Replacement for CopyListToObject for cases where object can not be passed by reference. The returned object must be assigned to object (property, list element, etc.) to which data is copied. More...

static void	CopyListToObject< DtoType, ObjectType > (DtoType[] tabDto, ref List< ObjectType > listObj)
	Copies array of DTOs (Data Transfer Objects) to a list of appropriate objects. More...

static DtoType[]	CopyListFromObjectReturned< DtoType, ObjectType > (List< ObjectType > tabObj, DtoType[] tabDto)
	Replacement for CopyArrayFromObject for cases where object can not be passed by reference. The returned object must be assigned to object (property, list element, etc.) to which data is copied. More...

static void	CopyListFromObject< DtoType, ObjectType > (List< ObjectType > tabObj, ref DtoType[] tabDto)
	Copies array of objects to a list of DTOs. More...

Detailed Description

Transfer Object (DTO) for neural network training set.

$A Igor Jul10; Tako78 Jun12;

Member Function Documentation

override NeuralTrainingParameters IG.Num.NeuralTrainingParametersDto.CreateObject ( )

inline

Creates and returns a new object of the corresponding type.

override void IG.Num.NeuralTrainingParametersDto.CopyFromPlain ( NeuralTrainingParameters trainingParameters )

inlineprotected

Copies the specified training parameters to the current DTO.

Parameters

trainingParameters Object that is copied to the current DTO.

override void IG.Num.NeuralTrainingParametersDto.CopyToPlain ( ref NeuralTrainingParameters trainingParameters )

inlineprotected

Copies contents of the current DTO to the specified training parameters object.

Parameters

trainingParameters Object that the current DTO content is copied to.

Member Data Documentation

double IG.Num.NeuralTrainingParametersDto.LearningRate

Learning rate.

double IG.Num.NeuralTrainingParametersDto.Momentum

Momentum. Specifies how much changes of weight in the previous iterations affect changes in the current iterations.

double IG.Num.NeuralTrainingParametersDto.SigmoidAlphaValue

Sigmoid alpha value (used in networks with sigmoid activation functions).

int IG.Num.NeuralTrainingParametersDto.InputLength

Gets or sets the number of input neurons.

int IG.Num.NeuralTrainingParametersDto.OutputLength

Gets or sets the number of output neurons.

double IG.Num.NeuralTrainingParametersDto.InputBoundSafetyFactor

double IG.Num.NeuralTrainingParametersDto.OutputBoundSafetyFactor

int IG.Num.NeuralTrainingParametersDto.MaxEpochs

Maximal number of epochs performed in the training procedure.

$A Tako78 Jul12;

int IG.Num.NeuralTrainingParametersDto.EpochsInBundle

Number of epochs in bundle (i.e. number of epochs performed at once, without any checks or output operations between).

This parameter does not affect the training procedure in terms of results.

$A Tako78 Jul12;

VectorDtoBase IG.Num.NeuralTrainingParametersDto.InputRange

Range from actual inputs.

$A Tako78 Octl12;

VectorDtoBase IG.Num.NeuralTrainingParametersDto.OutputRange

Range from actual outputs.

$A Tako78 Octl12;

VectorDtoBase IG.Num.NeuralTrainingParametersDto.ToleranceRms

Tolerance over RMS error of outputs over training points. Training will continue until error becomes below tolerance or until maximal number of epochs is reached. If less or equal than 0 then this tolerance is not taken into account.

$A Tako78 Jul12; Igor Jul12;

VectorDtoBase IG.Num.NeuralTrainingParametersDto.ToleranceRmsRelativeToRange

Relative tolerances on RMS errors of outputs over training points, relative to the correspoinding ranges of output data.

See also: NeuralApproximatorBase.ToleranceRmsRelativeToRange

double IG.Num.NeuralTrainingParametersDto.ToleranceRmsRelativeToRangeScalar = NeuralTrainingParameters.DefaultToleranceRmsRelativeToRangeScalar

Scalar through which all components of the Relative tolerances on RMS errors of outputs can be set to the same value.

See also: NeuralApproximatorBase.ToleranceRmsRelativeToRangeScalar

VectorDtoBase IG.Num.NeuralTrainingParametersDto.ToleranceMax

Tolerance on maximal error of outputs over training points. Training will continue until error becomes below tolerance or until maximal number of epochs is reached. If less or equal than 0 then this tolerance is not taken into account.

$A Tako78 Jul12;

VectorDtoBase IG.Num.NeuralTrainingParametersDto.ToleranceMaxRelativeToRange

Relative tolerances on max. abs. errors of outputs over training points, relative to the correspoinding ranges of output data.

See also: NeuralApproximatorBase.ToleranceMaxRelativeToRange

double IG.Num.NeuralTrainingParametersDto.ToleranceMaxRelativeToRangeScalar = NeuralTrainingParameters.DefaultToleranceMaxRelativeToRangeScalar

Scalar through which all components of the Relative tolerances on max. abs. errors of outputs can be set to the same value.

See also: NeuralApproximatorBase.ToleranceMaxRelativeToRangeScalar

int IG.Num.NeuralTrainingParametersDto.NumHiddenLayers

Number of Hideden layers.

$A Tako78 Jul12;

int [] IG.Num.NeuralTrainingParametersDto.NumHidenNeurons

Numbers of neurons in each hidden layer.

$A Tako78 Jul12;

bool IG.Num.NeuralTrainingParametersDto.IsNetworkTrained

Whether the network is trained (and results exist).

$A Tako78 Jul12;

VectorDtoBase IG.Num.NeuralTrainingParametersDto.ErrorsTrainingRms

RMS errors calculated on training data.

$A Tako78 Jul12;

VectorDtoBase [] IG.Num.NeuralTrainingParametersDto.ErrorsTrainingRmsTable

Convergence Table of RMS errors calculated on training data.

$A Tako78 Aug12;

VectorDtoBase IG.Num.NeuralTrainingParametersDto.ErrorsTrainingMax

Maximal errors calculated on training data.

$A Tako78 Jul12;

VectorDtoBase [] IG.Num.NeuralTrainingParametersDto.ErrorsTrainingMaxTable

Convergence Table of Maximal errors calculated on training data.

$A Tako78 Aug12;

VectorDtoBase IG.Num.NeuralTrainingParametersDto.ErrorsTrainingMeanAbs

Mean absolute errors calculated on training data.

$A Tako78 Jul12;

VectorDtoBase IG.Num.NeuralTrainingParametersDto.ErrorsVerificationRms

RMS errors calculated on verification data.

$A Tako78 Jul12;

VectorDtoBase [] IG.Num.NeuralTrainingParametersDto.ErrorsVerificationRmsTable

Convergence Table of RMS errors calculated on verification data.

$A Tako78 Aug12;

VectorDtoBase IG.Num.NeuralTrainingParametersDto.ErrorsVerificationMax

Maximal errors calculated on verification data.

$A Tako78 Jul12;

VectorDtoBase [] IG.Num.NeuralTrainingParametersDto.ErrorsVerificationMaxTable

Convergence Table of Maximal errors calculated on verification data.

$A Tako78 Aug12;

VectorDtoBase IG.Num.NeuralTrainingParametersDto.ErrorsVerificationMeanAbs

Maximal errors calculated on training data.

$A Tako78 Jul12;

List<VectorDtoBase> IG.Num.NeuralTrainingParametersDto.ErrorsRmsList

int IG.Num.NeuralTrainingParametersDto.NumEpochs

Number of epochs actually spent at training.

$A Tako78 Jul12;

double IG.Num.NeuralTrainingParametersDto.TrainingTime

Time spent for training.

$A Tako78 Jul12;;

double IG.Num.NeuralTrainingParametersDto.TrainingCpuTime

CPU time spent for training.

$A Tako78 Jul12;

int [] IG.Num.NeuralTrainingParametersDto.EpochNumbers

List of epoch numbers at which convergence data was sampled.

double [] IG.Num.NeuralTrainingParametersDto.EpochErrorsRms

List of sampled RMS errors corresponding to epoch numbers from EpochNumbers.

double [] IG.Num.NeuralTrainingParametersDto.EpochErrorsAbs

List of sampled absolute errors corresponding to epoch numbers from EpochNumbers.

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

igbase/numeric/approximation/neural/SerializationDtoNeural.cs

Public Member Functions

Public Attributes

Protected Member Functions

Additional Inherited Members

Detailed Description

Member Function Documentation

Member Data Documentation