NeurApp 1.1
NeurApp - software for exploring approximation by artificial neural networks on functions of one or two variables.

IG::Neural::NeuralTrainingParameters Class Reference

Contains Parameters that define neural network architecture and trainig procedure, together with achieved results after training such as various error norms. Not thread safe! More...

List of all members.

Classes

class  ComparerBase
 Base comparer class (implementation of the IComparer<NeuralTrainingParameters> interface) for conmparing objects of type NeuralTrainingParameters More...
class  ComparerErrorTrainingVector
class  ComparerTrainingTime

Public Member Functions

void SetEpochNumbers (int[] epochNumbers)
 Sets the list of epoch numbers at which convergence data was sampled.
void SetEpochNumbers (List< int > epochNumbers)
 Sets the list of epoch numbers at which convergence data was sampled.
void SetEpochErrorsRms (double[] errors)
 Sets the list of sampled RMS errors that correspond to epoch numbers from EpochNumbers.
void SetEpochErrorsRms (List< double > errors)
 Sets the list of sampled RMS errors corresponding to epoch numbers from EpochNumbers.
void SetEpochErrorsAbs (double[] errors)
 Sets the list of sampled absolute errors that correspond to epoch numbers from EpochNumbers.
void SetEpochErrorsAbs (List< double > errors)
 Sets the list of sampled absolute errors corresponding to epoch numbers from EpochNumbers.
void CopyFrom (NeuralApproximatorBase nn)
 Copies current data from the specified neural network approximator.
void CopyResultsFrom (NeuralApproximatorBase nn)
 Copies only results from the trained network to the current object.
void CopyTo (NeuralApproximatorBase nn)
 Copies data that determine neural network and training procedure (such as network architecture, training parameters, tolerances, etc.) from the current object to the specified neural network approximator. This enables to restore training contitions of a peviour training procedure.

Static Public Member Functions

static void SaveJson (NeuralTrainingParameters trainingParameters, string filePath)
 Saves (serializes) the specified training parameters object to the specified JSON file. File is owerwritten if it exists.
static void SaveJson (NeuralTrainingParameters trainingParameters, string filePath, bool append)
 Saves (serializes) the specified training parameters object to the specified JSON file.
static void LoadJson (string filePath, ref NeuralTrainingParameters trainingParametersRestored)
 Restores (deserializes) a training parameters object from the specified file in JSON format.
static void SaveJson (NeuralTrainingParameters[] trainingParameters, string filePath)
 Saves (serializes) the specified array of training parameters objects to the specified JSON file. File is owerwritten if it exists.
static void SaveJson (NeuralTrainingParameters[] trainingParameters, string filePath, bool append)
 Saves (serializes) the specified array of training parameters objects to the specified JSON file.
static void LoadJson (string filePath, ref NeuralTrainingParameters[] trainingParametersRestored)
 Restores (deserializes) an array of training parameters objects from the specified file in JSON format.
static void SaveJson (List< NeuralTrainingParameters > trainingParameters, string filePath)
 Saves (serializes) the specified list of training parameters objects to the specified JSON file. File is owerwritten if it exists.
static void SaveJson (List< NeuralTrainingParameters > trainingParameters, string filePath, bool append)
 Saves (serializes) the specified list of training parameters objects to the specified JSON file.
static void LoadJson (string filePath, ref List< NeuralTrainingParameters > trainingParametersRestored)
 Restores (deserializes) a list of training parameters objects from the specified file in JSON format.
static void SaveCSV (List< NeuralTrainingParameters > trainingParameters, string filePath)
 Saves the specified list of training parameters objects to the specified CSV file.
static ComparerTrainingTime CreateComparerTrainingTime ()

Public Attributes

List< IVector > _errorsTrainingRmsList = null
List< IVector > _errorsTrainingMaxList = null
List< IVector > _errorsVerificationRmsList = null
List< IVector > _errorsVerificationMaxList = null
bool _convergenceRmsEnabled = false

Static Public Attributes

static double DefaultLearningRate = 0.1
 Default value for learning rate in neural networks.
static double DefaultMomentum = 0.5
 Default value of momentum for neural networks.
static double DefaultSigmoidAlphaValue = 1.5
 Default value of the sigmoid alpha value (used in networks with sigmoid activation functions).
static int DefaultEpochsInBundle
 Default value for number of epochs in bundle (i.e. number of epochs performed at once, without any checks or output operations between).
static int DefaultNumHiddenLayers = 1
 Default number of hidden layers.
static int DefaultNumHiddenNeurons = 20
 Default number of hidden neurons in a layer.
static int DefaultMaxEpochs = 40000
 Default value for maximal number of epochs.
static IVector DefaultToleranceRms = null
 Default value for tollerance on RMS error in neural networks.
static IVector DefaultToleranceMax = null
 Default value for tollerance on max. abs. error in neural networks.
static double DefaultToleranceRmsRelativeToRangeScalar = 0.1
 Default value for the tolerance on RMS error, relative to the output range.
static double DefaultToleranceMaxRelativeToRangeScalar = 0
 Default value for the tolerance on max. abs. error, relative to the output range.
static int DefaultInputLength = 1
 Default number of input neurons.
static int DefaultOutputLength = 1
 Default number of output neurons.
static double DefaultInputBoundSafetyFactor = 1.5
 Default number of input safety factor.
static double DefaultOutputBoundSafetyFactor = 1.5
 Default number of output safety factor.

Protected Member Functions

IComparer< IVector > CreateComparerErrorTrainingRmsVector ()

Static Protected Member Functions

static double ErrorAverageCalc (List< IVector > ErrorConvergence, int NumLastErrors, int NumBundles, IVector scalingLength)
 Calculate average number of the desired number of first elements in the convergence list.
static double ErrorAverageCalc (List< IVector > ErrorConvergence, int NumLastErrors, int NumBundles)
 Calculate average number of the desired number of first elements in the convergence list.

Protected Attributes

double _learningRate = DefaultLearningRate
double _momentum = DefaultMomentum
double _sigmoidAlphaValue = DefaultSigmoidAlphaValue
int _maxEpochs = DefaultMaxEpochs
int _epochInBundle = DefaultEpochsInBundle
IVector _outputRange
IBoundingBox _outputNeuronRange
IVector _inputRange
IBoundingBox _inputNeuronRange
IVector _toleranceRms
IVector _toleranceMax
int _numHiddenLayers = DefaultNumHiddenLayers
int[] _numHiddenNeurons = null
bool _isNetworkTrained = false
IVector _errorsTrainingRms
IVector _errorsTrainingMax
IVector _errorsTrainingMeanAbs
IVector _errorsVerificationRms
IVector _errorsVerificationMax
IVector _errorsVerificationMeanAbs
int _numEpochs = 0
double _trainingTime = 0
double _trainingCpuTime = 0
List< int > _EpochNumbers
List< double > _EpochErrorsRms
List< double > _EpochErrorsAbs

Properties

double LearningRate [get, set]
 Learning rate.
double Momentum [get, set]
 Momentum. Specifies how much changes of weight in the previous iterations affect changes in the current iterations.
double SigmoidAlphaValue [get, set]
 Sigmoid alpha value (used in networks with sigmoid activation functions).
virtual int InputLength [get, set]
 Gets or sets the number of input neurons.
virtual int OutputLength [get, set]
 Gets or sets the number of output neurons.
virtual double InputBoundSafetyFactor [get, set]
 Gets or sets input safety factor.
virtual double OutputBoundSafetyFactor [get, set]
 Gets or sets output safety factor.
int MaxEpochs [get, set]
 Maximal number of epochs performed in the training procedure.
int EpochsInBundle [get, set]
 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.
IVector OutputRange [get, set]
 Range from actual outputs.
IBoundingBox OutputNeuronRange [get, set]
 Bounding box from actual outputs.
IVector InputRange [get, set]
 Range from actual inputs.
IBoundingBox InputNeuronRange [get, set]
 Bounding box from actual inputs.
IVector ToleranceRms [get, set]
 Tolerance over RMS error of output 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.
IVector ToleranceMax [get, set]
 Tolerance on maximal error of output 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.
IVector ToleranceRmsRelativeToRange [get, set]
 Relative tolerances on RMS errors of outputs over training points, relative to the correspoinding ranges of output data.
double ToleranceRmsRelativeToRangeScalar [get, set]
 Scalar through which all components of the Relative tolerances on RMS errors of outputs can be set to the same value.
IVector ToleranceMaxRelativeToRange [get, set]
 Relative tolerances on max. abs. errors of outputs over training points, relative to the correspoinding ranges of output data.
double ToleranceMaxRelativeToRangeScalar [get, set]
 Scalar through which all components of the Relative tolerances on max. abs. errors of outputs can be set to the same value.
int NumHiddenLayers [get, set]
 Number of Hideden layers.
int[] NumHidenNeurons [get, set]
 Numbers of neurons in each hidden layer.
bool IsNetworkTrained [get, set]
 Whether the network is trained (and results exist).
IVector ErrorsTrainingRms [get, set]
 RMS errors calculated on training data.
List< IVector > ErrorsTrainingRmsList [get, set]
 Convergence List of Rms errors calculated on training data.
IVector ErrorsTrainingMax [get, set]
 Maximal errors calculated on training data.
List< IVector > ErrorsTrainingMaxList [get, set]
 Convergence List of Maximal errors calculated on training data.
IVector ErrorsTrainingMeanAbs [get, set]
 Mean absolute errors calculated on training data.
IVector ErrorsVerificationRms [get, set]
 RMS errors calculated on verification data.
List< IVector > ErrorsVerificationRmsList [get, set]
 Convergence List of RMS errors calculated on verification data.
IVector ErrorsVerificationMax [get, set]
 Maximal errors calculated on verification data.
List< IVector > ErrorsVerificationMaxList [get, set]
 Convergence List of Maximal errors calculated on verification data.
IVector ErrorsVerificationMeanAbs [get, set]
 Maximal errors calculated on training data.
bool SaveConvergenceRms [get, set]
int NumEpochs [get, set]
 Number of epochs actually spent at training. This may be less than MaxEpochs if convergence is reached before.
double TrainingTime [get, set]
 Time spent for training.
double TrainingCpuTime [get, set]
 CPU time spent for training.
List< int > EpochNumbers [get, set]
 List of epoch numbers at which convergence data was sampled.
List< double > EpochErrorsRms [get, set]
 List of sampled RMS errors corresponding to epoch numbers from EpochNumbers.
List< double > EpochErrorsAbs [get, set]
 List of sampled absolute errors corresponding to epoch numbers from EpochNumbers.

Private Attributes

int _inputLength = DefaultInputLength
int _outputLength = DefaultOutputLength
double _inputBoundSafetyFactor = DefaultInputBoundSafetyFactor
 Gets or sets input safety factor.
double _outputBoundSafetyFactor = DefaultOutputBoundSafetyFactor
 Gets or sets output safety factor.
IVector _tolRmsRelative
 Auxiliary properties for defining tolerances in a relative way:
double _tolRmsRelativeScalar = DefaultToleranceRmsRelativeToRangeScalar
IVector _tolMaxRelative
double _tolMaxRelativeScalar = DefaultToleranceMaxRelativeToRangeScalar

Detailed Description

Contains Parameters that define neural network architecture and trainig procedure, together with achieved results after training such as various error norms.

Not thread safe!

This class is used for storing parameters of neural networks and restoring them at a later time, in order to repeat training under similar condition or simply to analyse performance of neural networks. $A Igor May12;


Member Function Documentation

void IG::Neural::NeuralTrainingParameters::SetEpochNumbers ( int[]  epochNumbers) [inline]

Sets the list of epoch numbers at which convergence data was sampled.

Parameters:
epochNumbersArray of epoch numbers from which data is copied.
void IG::Neural::NeuralTrainingParameters::SetEpochNumbers ( List< int >  epochNumbers) [inline]

Sets the list of epoch numbers at which convergence data was sampled.

Parameters:
epochNumbersList of epoch numbers from which data is copied.
void IG::Neural::NeuralTrainingParameters::SetEpochErrorsRms ( double[]  errors) [inline]

Sets the list of sampled RMS errors that correspond to epoch numbers from EpochNumbers.

Parameters:
errorsArray from which data is copied.
void IG::Neural::NeuralTrainingParameters::SetEpochErrorsRms ( List< double >  errors) [inline]

Sets the list of sampled RMS errors corresponding to epoch numbers from EpochNumbers.

Parameters:
errorsList from which data is copied.
void IG::Neural::NeuralTrainingParameters::SetEpochErrorsAbs ( double[]  errors) [inline]

Sets the list of sampled absolute errors that correspond to epoch numbers from EpochNumbers.

Parameters:
errorsArray from which data is copied.
void IG::Neural::NeuralTrainingParameters::SetEpochErrorsAbs ( List< double >  errors) [inline]

Sets the list of sampled absolute errors corresponding to epoch numbers from EpochNumbers.

Parameters:
errorsList from which data is copied.
void IG::Neural::NeuralTrainingParameters::CopyFrom ( NeuralApproximatorBase  nn) [inline]

Copies current data from the specified neural network approximator.

Parameters:
nnNeural network approximator that data is copied form.
void IG::Neural::NeuralTrainingParameters::CopyResultsFrom ( NeuralApproximatorBase  nn) [inline]

Copies only results from the trained network to the current object.

Parameters:
nnNeural network approximator which results are copied from.
void IG::Neural::NeuralTrainingParameters::CopyTo ( NeuralApproximatorBase  nn) [inline]

Copies data that determine neural network and training procedure (such as network architecture, training parameters, tolerances, etc.) from the current object to the specified neural network approximator. This enables to restore training contitions of a peviour training procedure.

Parameters:
nnNeural network approximator that data is copied to.
static void IG::Neural::NeuralTrainingParameters::SaveJson ( NeuralTrainingParameters  trainingParameters,
string  filePath 
) [inline, static]

Saves (serializes) the specified training parameters object to the specified JSON file. File is owerwritten if it exists.

Parameters:
trainingParametersObject that is saved to a file.
filePathPath to the file into which object is is saved.
static void IG::Neural::NeuralTrainingParameters::SaveJson ( NeuralTrainingParameters  trainingParameters,
string  filePath,
bool  append 
) [inline, static]

Saves (serializes) the specified training parameters object to the specified JSON file.

Parameters:
trainingParametersObject that is saved to a file.
filePathPath to the file into which object is is saved.
appendSpecifies whether serialized data is appended at the end of the file in the case that the file already exists.
static void IG::Neural::NeuralTrainingParameters::LoadJson ( string  filePath,
ref NeuralTrainingParameters  trainingParametersRestored 
) [inline, static]

Restores (deserializes) a training parameters object from the specified file in JSON format.

Parameters:
filePathFile from which object data is restored.
trainingParametersRestoredObject that is restored by deserialization.
static void IG::Neural::NeuralTrainingParameters::SaveJson ( NeuralTrainingParameters[]  trainingParameters,
string  filePath 
) [inline, static]

Saves (serializes) the specified array of training parameters objects to the specified JSON file. File is owerwritten if it exists.

Parameters:
trainingParametersArray that is saved to a file.
filePathPath to the file into which object is is saved.
static void IG::Neural::NeuralTrainingParameters::SaveJson ( NeuralTrainingParameters[]  trainingParameters,
string  filePath,
bool  append 
) [inline, static]

Saves (serializes) the specified array of training parameters objects to the specified JSON file.

Parameters:
trainingParametersArray that is saved to a file.
filePathPath to the file into which object is is saved.
appendSpecifies whether serialized data is appended at the end of the file in the case that the file already exists.
static void IG::Neural::NeuralTrainingParameters::LoadJson ( string  filePath,
ref NeuralTrainingParameters[]  trainingParametersRestored 
) [inline, static]

Restores (deserializes) an array of training parameters objects from the specified file in JSON format.

Parameters:
filePathFile from which array of objects is restored.
trainingParametersRestoredArray of objects that is restored by deserialization.
static void IG::Neural::NeuralTrainingParameters::SaveJson ( List< NeuralTrainingParameters trainingParameters,
string  filePath 
) [inline, static]

Saves (serializes) the specified list of training parameters objects to the specified JSON file. File is owerwritten if it exists.

Parameters:
trainingParametersList that is saved to a file.
filePathPath to the file into which object is is saved.
static void IG::Neural::NeuralTrainingParameters::SaveJson ( List< NeuralTrainingParameters trainingParameters,
string  filePath,
bool  append 
) [inline, static]

Saves (serializes) the specified list of training parameters objects to the specified JSON file.

Parameters:
trainingParametersList that is saved to a file.
filePathPath to the file into which object is is saved.
appendSpecifies whether serialized data is appended at the end of the file in the case that the file already exists.
static void IG::Neural::NeuralTrainingParameters::LoadJson ( string  filePath,
ref List< NeuralTrainingParameters trainingParametersRestored 
) [inline, static]

Restores (deserializes) a list of training parameters objects from the specified file in JSON format.

Parameters:
filePathFile from which list of objects is restored.
trainingParametersRestoredArray of objects that is restored by deserialization.
static void IG::Neural::NeuralTrainingParameters::SaveCSV ( List< NeuralTrainingParameters trainingParameters,
string  filePath 
) [inline, static]

Saves the specified list of training parameters objects to the specified CSV file.

Parameters:
trainingParametersList that is saved to a file.
filePathPath to the file into which object is is saved.

$A Tako78 Sep12;

static double IG::Neural::NeuralTrainingParameters::ErrorAverageCalc ( List< IVector >  ErrorConvergence,
int  NumLastErrors,
int  NumBundles,
IVector  scalingLength 
) [inline, static, protected]

Calculate average number of the desired number of first elements in the convergence list.

Parameters:
ErrorConvergenceList of convergence errors.
NumLastErrorsNumber of elemnts in the convergence list.
Returns:
Average number.
static double IG::Neural::NeuralTrainingParameters::ErrorAverageCalc ( List< IVector >  ErrorConvergence,
int  NumLastErrors,
int  NumBundles 
) [inline, static, protected]

Calculate average number of the desired number of first elements in the convergence list.

Parameters:
ErrorConvergenceList of convergence errors.
NumLastErrorsNumber of elemnts in the convergence list.
Returns:
Average number.
IComparer<IVector> IG::Neural::NeuralTrainingParameters::CreateComparerErrorTrainingRmsVector ( ) [inline, protected]
static ComparerTrainingTime IG::Neural::NeuralTrainingParameters::CreateComparerTrainingTime ( ) [inline, static]

Member Data Documentation

Default value for learning rate in neural networks.

Default value of momentum for neural networks.

Default value of the sigmoid alpha value (used in networks with sigmoid activation functions).

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

Default number of hidden layers.

Default number of hidden neurons in a layer.

Default value for maximal number of epochs.

Default value for tollerance on RMS error in neural networks.

Default value for tollerance on max. abs. error in neural networks.

Default value for the tolerance on RMS error, relative to the output range.

Default value for the tolerance on max. abs. error, relative to the output range.

Default number of input neurons.

Default number of output neurons.

Default number of input safety factor.

Default number of output safety factor.

Auxiliary properties for defining tolerances in a relative way:


Property Documentation

double IG::Neural::NeuralTrainingParameters::LearningRate [get, set]

Learning rate.

double IG::Neural::NeuralTrainingParameters::Momentum [get, set]

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

double IG::Neural::NeuralTrainingParameters::SigmoidAlphaValue [get, set]

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

virtual int IG::Neural::NeuralTrainingParameters::InputLength [get, set]

Gets or sets the number of input neurons.

virtual int IG::Neural::NeuralTrainingParameters::OutputLength [get, set]

Gets or sets the number of output neurons.

virtual double IG::Neural::NeuralTrainingParameters::InputBoundSafetyFactor [get, set]

Gets or sets input safety factor.

virtual double IG::Neural::NeuralTrainingParameters::OutputBoundSafetyFactor [get, set]

Gets or sets output safety factor.

int IG::Neural::NeuralTrainingParameters::MaxEpochs [get, set]

Maximal number of epochs performed in the training procedure.

int IG::Neural::NeuralTrainingParameters::EpochsInBundle [get, set]

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.

IVector IG::Neural::NeuralTrainingParameters::OutputRange [get, set]

Range from actual outputs.

$A Tako78 Octl12;

IBoundingBox IG::Neural::NeuralTrainingParameters::OutputNeuronRange [get, set, protected]

Bounding box from actual outputs.

$A Tako78 Octl12;

IVector IG::Neural::NeuralTrainingParameters::InputRange [get, set]

Range from actual inputs.

$A Tako78 Octl12;

IBoundingBox IG::Neural::NeuralTrainingParameters::InputNeuronRange [get, set, protected]

Bounding box from actual inputs.

$A Tako78 Octl12;

IVector IG::Neural::NeuralTrainingParameters::ToleranceRms [get, set]

Tolerance over RMS error of output 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.

IVector IG::Neural::NeuralTrainingParameters::ToleranceMax [get, set]

Tolerance on maximal error of output 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.

IVector IG::Neural::NeuralTrainingParameters::ToleranceRmsRelativeToRange [get, set]

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

See also:
NeuralApproximatorBase.ToleranceRmsRelativeToRange
double IG::Neural::NeuralTrainingParameters::ToleranceRmsRelativeToRangeScalar [get, set]

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
IVector IG::Neural::NeuralTrainingParameters::ToleranceMaxRelativeToRange [get, set]

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::Neural::NeuralTrainingParameters::ToleranceMaxRelativeToRangeScalar [get, set]

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::Neural::NeuralTrainingParameters::NumHiddenLayers [get, set]

Number of Hideden layers.

int [] IG::Neural::NeuralTrainingParameters::NumHidenNeurons [get, set]

Numbers of neurons in each hidden layer.

bool IG::Neural::NeuralTrainingParameters::IsNetworkTrained [get, set]

Whether the network is trained (and results exist).

IVector IG::Neural::NeuralTrainingParameters::ErrorsTrainingRms [get, set]

RMS errors calculated on training data.

List<IVector> IG::Neural::NeuralTrainingParameters::ErrorsTrainingRmsList [get, set]

Convergence List of Rms errors calculated on training data.

IVector IG::Neural::NeuralTrainingParameters::ErrorsTrainingMax [get, set]

Maximal errors calculated on training data.

List<IVector> IG::Neural::NeuralTrainingParameters::ErrorsTrainingMaxList [get, set]

Convergence List of Maximal errors calculated on training data.

IVector IG::Neural::NeuralTrainingParameters::ErrorsTrainingMeanAbs [get, set]

Mean absolute errors calculated on training data.

IVector IG::Neural::NeuralTrainingParameters::ErrorsVerificationRms [get, set]

RMS errors calculated on verification data.

List<IVector> IG::Neural::NeuralTrainingParameters::ErrorsVerificationRmsList [get, set]

Convergence List of RMS errors calculated on verification data.

IVector IG::Neural::NeuralTrainingParameters::ErrorsVerificationMax [get, set]

Maximal errors calculated on verification data.

List<IVector> IG::Neural::NeuralTrainingParameters::ErrorsVerificationMaxList [get, set]

Convergence List of Maximal errors calculated on verification data.

IVector IG::Neural::NeuralTrainingParameters::ErrorsVerificationMeanAbs [get, set]

Maximal errors calculated on training data.

bool IG::Neural::NeuralTrainingParameters::SaveConvergenceRms [get, set]
int IG::Neural::NeuralTrainingParameters::NumEpochs [get, set]

Number of epochs actually spent at training. This may be less than MaxEpochs if convergence is reached before.

double IG::Neural::NeuralTrainingParameters::TrainingTime [get, set]

Time spent for training.

double IG::Neural::NeuralTrainingParameters::TrainingCpuTime [get, set]

CPU time spent for training.

List<int> IG::Neural::NeuralTrainingParameters::EpochNumbers [get, set]

List of epoch numbers at which convergence data was sampled.

List<double> IG::Neural::NeuralTrainingParameters::EpochErrorsRms [get, set]

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

List<double> IG::Neural::NeuralTrainingParameters::EpochErrorsAbs [get, set]

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


The documentation for this class was generated from the following file:
 All Classes Namespaces Files Functions Variables Enumerations Properties