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

IG::Neural::NeuralTrainingLimits Class Reference

Contains Parameters that define neural network architecture limits and trainig parameter limits. Not thread safe! More...

List of all members.

Public Member Functions

void PrepareNumHiddenNeuronsValuesArray (int numLayers, params int[] numHiddenNeuronsValues)
 Prepares values of numbers of neurons in individual layers according to parameters. For each layer, numbers of neurons in that layers to be used in the table are the same.
void PrepareNumHiddenNeuronsValuesArray (int numLayers, int minNumNeurons, int maxNumNeurons, int numValues, double intervalGrowthFactor)
 Prepares values of numbers of neurons in individual layers according to parameters in such a way that intervals between these values grow exponentially.
delegate void DoForParameters (List< NeuralTrainingParameters > trainingParameters, List< int > dimensions, int which)
void DoForParameters_CreateTable (List< NeuralTrainingParameters > trainingParameters, List< int > dimensions, int which)
void CreateTrainingTable (List< NeuralTrainingParameters > trainingParameters, List< int > tableDimensions)
 Creates a table of training parameters.
void CreateTrainingTable (List< NeuralTrainingParameters > trainingParameters)
 Creates a table of training parameters.
void IterateThroughMultidimensionalTable (List< NeuralTrainingParameters > tableResults, List< int > tableDimensions, bool createTable, bool createDimensions, DoForParameters doOnElement)
 Iterates through all elements of the table of training results defined by the current object, and does whatever is specified by the parameters.

Static Public Member Functions

static void SaveJson (NeuralTrainingLimits trainingLimits, string filePath)
 Saves (serializes) the specified array of training limits objects to the specified JSON file. File is owerwritten if it exists.
static void SaveJson (NeuralTrainingLimits trainingLimits, string filePath, bool append)
 Saves (serializes) the specified array of training limits objects to the specified JSON file.
static void LoadJson (string filePath, ref NeuralTrainingLimits trainingLimits)
 Restores (deserializes) an array of training parameters objects from the specified file in JSON format.

Static Public Attributes

static double DefaultLearningRateMin = 0.1
 Default value for minimum learning rate in neural networks.
static double DefaultLearningRateMax = 0.6
 Default value for maximum learning rate in neural networks.
static int DefaultLearningRateNum = 5
 Default value for number of learning rates in neural networks.
static double DefaultMomentumMin = 0.3
 Default value for minimum momentum in neural networks.
static double DefaultMomentumMax = 0.8
 Default value for maximum momentum in neural networks.
static int DefaultMomentumNum = 5
 Default value for number of momentums in neural networks.
static double DefaultAlphaMin = 1.0
 Default value for minimum alpha value in neural networks.
static double DefaultAlphaMax = 2.0
 Default value for maximum alpha value in neural networks.
static int DefaultAlphaNum = 5
 Default value for number of alpha values in neural networks.
static double DefaultInputSafetyFactorMin = 1.4
 Default value for minimum input bound safety factor value in neural networks.
static double DefaultInputSafetyFactorMax = 1.4
 Default value for maximum input bound safety factor value in neural networks.
static int DefaultInputSafetyFactorNum = 1
 Default value for number of input bound safety factors values in neural networks.
static double DefaultOutputSafetyFactorMin = 1.4
 Default value for minimum output bound safety factor value in neural networks.
static double DefaultOutputSafetyFactorMax = 1.4
 Default value for maximum output bound safety factor value in neural networks.
static int DefaultOutputSafetyFactorNum = 1
 Default value for number of output bound safety factors values in neural networks.
static bool DefaultEnableArchitectureTest = false
 Default flag for enabling different layers in neural networks.
static int DefaultNumHiddenLayersNum = 1
 Default value for number of hidden layers in neural networks.
static int DefaultNumHiddenNeuronsFirstMin = 5
 Default value for number of hidden neurons in first hidden layer in neural networks.
static int DefaultNumHiddenNeuronsFirstMax = 25
 Default value for number of hidden neurons in first hidden layer in neural networks.
static int DefaultNumHiddenNeuronsFirstNum = 1
 Default value for number of hidden neurons in first hidden layer in neural networks.
static int DefaultNumHiddenNeuronsSecondMin = 2
 Default value for number of hidden neurons in second hidden layer in neural networks.
static int DefaultNumHiddenNeuronsSecondMax = 10
 Default value for number of hidden neurons in second hidden layer in neural networks.
static int DefaultNumHiddenNeuronsSecondNum = 1
 Default value for number of hidden neurons in second hidden layer in neural networks.
static int DefaultNumHiddenNeuronsThirdMin = 2
 Default value for number of hidden neurons in third hidden layer in neural networks.
static int DefaultNumHiddenNeuronsThirdMax = 10
 Default value for number of hidden neurons in third hidden layer in neural networks.
static int DefaultNumHiddenNeuronsThirdNum = 1
 Default value for number of hidden neurons in third hidden layer in neural networks.
static int DefaultMaxEpochs = 1000
 Default value for maximum number of epochs in neural networks.
static int DefaultEpochBundle = 100
 Default value for number of epochs in bundle in neural networks.
static bool DefaultEnableRangeTolerance = false
 Flag for enabling toelrance that represent a percentage of the output range.
static int DefaultInputLenght = 5
 Default value for number of input neurons.
static int DefaultOutputLenght = 3
 Default value for number of output neurons.

Protected Member Functions

int[] GetArrayCopy (int[] original)
 Creates and returns a copy of the specified array of integers.
int[] GetArrayCopyInt (double[] original)
 Creates and returns an array of integers that is a copy of the specified array of double values (double to integer conversion made by rounding).

Protected Attributes

double _learningRateMin = NeuralTrainingParameters.DefaultLearningRate
double _learningRateMax = NeuralTrainingParameters.DefaultLearningRate
int _learningRateNum = 1
double _momentumMin = DefaultMomentumMin
double _momentumMax = DefaultMomentumMax
int _momentumNum = DefaultMomentumNum
double _alphaMin = DefaultAlphaMin
double _alphaMax = DefaultAlphaMax
int _alphaNum = DefaultAlphaNum
double _inputSafetyFactorMin = DefaultInputSafetyFactorMin
double _inputSafetyFactorMax = DefaultInputSafetyFactorMax
int _inputSafetyFactorNum = DefaultInputSafetyFactorNum
double _outputSafetyFactorMin = DefaultOutputSafetyFactorMin
double _outputSafetyFactorMax = DefaultOutputSafetyFactorMax
int _outputSafetyFactorNum = DefaultOutputSafetyFactorNum
int _maxEpochs = DefaultMaxEpochs
int _epochBundle = DefaultEpochBundle
int _inputLenght = DefaultInputLenght
int _outputLenght = DefaultOutputLenght
bool _enableRangeTolerance = DefaultEnableRangeTolerance
IVector _toleranceRms
IVector _toleranceMax
bool _enableArchitectureTest = DefaultEnableArchitectureTest
int _numHiddenLayersNum = DefaultNumHiddenLayersNum
int _numHiddenNeuronsFirstMin = DefaultNumHiddenNeuronsFirstMin
int _numHiddenNeuronsFirstMax = DefaultNumHiddenNeuronsFirstMax
int _numHiddenNeuronsFirstNum = DefaultNumHiddenNeuronsFirstNum
int[] _numHiddenNeuronsFirstValues
bool randomTableEnabled = false
int _numHiddenNeuronsSecondMin = DefaultNumHiddenNeuronsSecondMin
int _numHiddenNeuronsSecondMax = DefaultNumHiddenNeuronsSecondMax
int _numHiddenNeuronsSecondNum = DefaultNumHiddenNeuronsSecondNum
int[] _numHiddenNeuronsSecondValues
int _numHiddenNeuronsThirdMin = DefaultNumHiddenNeuronsThirdMin
int _numHiddenNeuronsThirdMax = DefaultNumHiddenNeuronsThirdMax
int _numHiddenNeuronsThirdNum = DefaultNumHiddenNeuronsThirdNum
int[] _numHiddenNeuronsThirdValues

Properties

double LearningRateMin [get, set]
 Minimum limit for learning rate.
double LearningRateMax [get, set]
 Maximum limit for learning rate.
int LearningRateNum [get, set]
 Number of learning rates.
double MomentumMin [get, set]
 Minimum limit for momentum.
double MomentumMax [get, set]
 Maximum limit for momentum.
int MomentumNum [get, set]
 Number of momentums.
double AlphaMin [get, set]
 Minimum limit for alpha value.
double AlphaMax [get, set]
 Maximum limit for alpha value.
int AlphaNum [get, set]
 Number of alpha value.
double InputSafetyFactorMin [get, set]
 Minimum limit for input safety factor value.
double InputSafetyFactorMax [get, set]
 Maximum limit for input safety factor value.
int InputSafetyFactorNum [get, set]
 Number of input safety factor values.
double OutputSafetyFactorMin [get, set]
 Minimum limit for output safety factor value.
double OutputSafetyFactorMax [get, set]
 Maximum limit for output safety factor value.
int OutputSafetyFactorNum [get, set]
 Number of output safety factor values.
int MaxEpochs [get, set]
 Maximum number of epochs performed in training.
int EpochBundle [get, set]
 Number of epochs in boundle.
int InputLenght [get, set]
 Number of input neurons.
int OutputLength [get, set]
 Number of output neurons.
bool EnableRangeTolerance [get, set]
 Flag for enabling toelrance that represent a percentage of the output range.
IVector ToleranceRms [get, set]
 Tolerance for RMS.
IVector ToleranceMax [get, set]
 Maximum tolerance for max. abs. difference.
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.
bool EnableArchitectureTest [get, set]
 Flag for enabling test in architecture of ANN.
int NumHiddenLayersNum [get, set]
 Number of hidden layers in neural network.
int NumHiddenNeuronsFirstMin [get, set]
 Minimum number of hidden neurons in first hidden layer.
int NumHiddenNeuronsFirstMax [get, set]
 Maximum number of hidden neurons in first hidden layer.
int NumHiddenNeuronsFirstNum [get, set]
 Number of hidden neurons in first hidden layer.
int[] NumHiddenNeuronsFirstValues [get, set]
 Values of number of hidden neurons in the first layers that will appear in the table.
int NumHiddenNeuronsSecondMin [get, set]
 Minimum number of hidden neurons in second hidden layer.
int NumHiddenNeuronsSecondMax [get, set]
 Maximum number of hidden neurons in second hidden layer.
int NumHiddenNeuronsSecondNum [get, set]
 Number of hidden neurons in second hidden layer.
int[] NumHiddenNeuronsSecondValues [get, set]
 Values of number of hidden neurons in the second layers that will appear in the table.
int NumHiddenNeuronsThirdMin [get, set]
 Minimum number of hidden neurons in third hidden layer.
int NumHiddenNeuronsThirdMax [get, set]
 Maximum number of hidden neurons in third hidden layer.
int NumHiddenNeuronsThirdNum [get, set]
 Number of hidden neurons in third hidden layer.
int[] NumHiddenNeuronsThirdValues [get, set]
 Values of number of hidden neurons in the third layer that will appear in the table.

Private Member Functions

void PrepareNeuronsTable (int minNeurons, int maxNeurons, int numNeurons, double growthFactorref, ref int[] neurpnsTable)
 Prepares table of neurons in geometric sequence.
void PrepareNeuronTable (ref int[] neuronsFirstLayer, ref int[] neuronsSecondLayer, ref int[] neuronsThirdLayer)

Private Attributes

IVector _tolRmsRelative
 Auxiliary properties for defining tolerances in a relative way:
double _tolRmsRelativeScalar = NeuralTrainingParameters.DefaultToleranceRmsRelativeToRangeScalar
IVector _tolMaxRelative
double _tolMaxRelativeScalar = NeuralTrainingParameters.DefaultToleranceMaxRelativeToRangeScalar

Detailed Description

Contains Parameters that define neural network architecture limits and trainig parameter limits.

Not thread safe!

This class is used for storing training parameter limits 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 Tako78 Aug12; Igor Aug12 Nov12;


Member Function Documentation

int [] IG::Neural::NeuralTrainingLimits::GetArrayCopy ( int[]  original) [inline, protected]

Creates and returns a copy of the specified array of integers.

Parameters:
originalArray whose copy is returned.
int [] IG::Neural::NeuralTrainingLimits::GetArrayCopyInt ( double[]  original) [inline, protected]

Creates and returns an array of integers that is a copy of the specified array of double values (double to integer conversion made by rounding).

Parameters:
originalArray whose copy is returned.
void IG::Neural::NeuralTrainingLimits::PrepareNumHiddenNeuronsValuesArray ( int  numLayers,
params int[]  numHiddenNeuronsValues 
) [inline]

Prepares values of numbers of neurons in individual layers according to parameters. For each layer, numbers of neurons in that layers to be used in the table are the same.

Parameters:
numLayersNumber of hidden layers (this is fixed for the tables where this method is used; the containing class also does not support tables where number of layers would vary).
numHiddenNeuronsValuesValues for the number of hidden neurons in different layers (common for all layers).
void IG::Neural::NeuralTrainingLimits::PrepareNumHiddenNeuronsValuesArray ( int  numLayers,
int  minNumNeurons,
int  maxNumNeurons,
int  numValues,
double  intervalGrowthFactor 
) [inline]

Prepares values of numbers of neurons in individual layers according to parameters in such a way that intervals between these values grow exponentially.

Parameters:
numLayersNumber of hidden layers (this is fixed for the tables where this method is used; the containing class also does not support tables where number of layers would vary).
minNumNeuronsMinimal value for the number fo neurons in hidden layers.
maxNumNeuronsMaxmial value for the number of neurons in hidden layers.
numValuesNumber of values for the number of neurons in hidden layers.
intervalGrowthFactorFactor by which length of each next iterval befoore successive values for the number of neurons in hidden layers is extended.
delegate void IG::Neural::NeuralTrainingLimits::DoForParameters ( List< NeuralTrainingParameters trainingParameters,
List< int >  dimensions,
int  which 
)
void IG::Neural::NeuralTrainingLimits::DoForParameters_CreateTable ( List< NeuralTrainingParameters trainingParameters,
List< int >  dimensions,
int  which 
) [inline]
void IG::Neural::NeuralTrainingLimits::CreateTrainingTable ( List< NeuralTrainingParameters trainingParameters,
List< int >  tableDimensions 
) [inline]

Creates a table of training parameters.

Parameters:
trainingParametersList where table of parameters is stored. Must be different than null. Eventual elements already contained will be deleted.
tableDimensionsList of dimensions of the generated table. If specified then table dimensions will be put on the list (the list is cleared at the beinning).
void IG::Neural::NeuralTrainingLimits::CreateTrainingTable ( List< NeuralTrainingParameters trainingParameters) [inline]

Creates a table of training parameters.

Parameters:
trainingParametersList where table of parameters is stored. Must be different than null. Eventual elements already contained will be deleted.
void IG::Neural::NeuralTrainingLimits::PrepareNeuronsTable ( int  minNeurons,
int  maxNeurons,
int  numNeurons,
double  growthFactorref,
ref int[]  neurpnsTable 
) [inline, private]

Prepares table of neurons in geometric sequence.

Parameters:
minNeuronsMinimum number of neurons.
maxNeuronsMaximum number of neurons.
numNeuronsNumber of neurons in sequence.
neurpnsTableTable of neurons.

$A Tako78 Nov12;

void IG::Neural::NeuralTrainingLimits::PrepareNeuronTable ( ref int[]  neuronsFirstLayer,
ref int[]  neuronsSecondLayer,
ref int[]  neuronsThirdLayer 
) [inline, private]
void IG::Neural::NeuralTrainingLimits::IterateThroughMultidimensionalTable ( List< NeuralTrainingParameters tableResults,
List< int >  tableDimensions,
bool  createTable,
bool  createDimensions,
DoForParameters  doOnElement 
) [inline]

Iterates through all elements of the table of training results defined by the current object, and does whatever is specified by the parameters.

Parameters:
tableResultsTable where training parameters and results are stored. Must be specified when this table is created (i.e. parameter createTable is true) or when something must be done on each element (i.e. function parameter is doOnElement defined).
tableDimensionsTable where dimensions are stored. Must be specified when the table of dimensions will be created (i.e. the parameter createDimensions is true).
createTableSpecifies whether the table of training parameters and results will be created by the function call. If true then the parameter tableResults must be specified.
createDimensionsSpecifies whether the table of dimensions will be created when iterating over elements. If true then the parameter tableDimensions must be specified.
doOnElementDelegate that is executed on each element of the table. Index of the current element, as well as the table of the resulet (parameter tableResults ) and the table of dimensions (parameter tableDimensions ) are passed to the delegate when executed.
static void IG::Neural::NeuralTrainingLimits::SaveJson ( NeuralTrainingLimits  trainingLimits,
string  filePath 
) [inline, static]

Saves (serializes) the specified array of training limits 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::NeuralTrainingLimits::SaveJson ( NeuralTrainingLimits  trainingLimits,
string  filePath,
bool  append 
) [inline, static]

Saves (serializes) the specified array of training limits 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::NeuralTrainingLimits::LoadJson ( string  filePath,
ref NeuralTrainingLimits  trainingLimits 
) [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.

Member Data Documentation

Default value for minimum learning rate in neural networks.

Default value for maximum learning rate in neural networks.

Default value for number of learning rates in neural networks.

Default value for minimum momentum in neural networks.

Default value for maximum momentum in neural networks.

Default value for number of momentums in neural networks.

Default value for minimum alpha value in neural networks.

Default value for maximum alpha value in neural networks.

Default value for number of alpha values in neural networks.

Default value for minimum input bound safety factor value in neural networks.

Default value for maximum input bound safety factor value in neural networks.

Default value for number of input bound safety factors values in neural networks.

Default value for minimum output bound safety factor value in neural networks.

Default value for maximum output bound safety factor value in neural networks.

Default value for number of output bound safety factors values in neural networks.

Default flag for enabling different layers in neural networks.

Default value for number of hidden layers in neural networks.

Default value for number of hidden neurons in first hidden layer in neural networks.

Default value for number of hidden neurons in first hidden layer in neural networks.

Default value for number of hidden neurons in first hidden layer in neural networks.

Default value for number of hidden neurons in second hidden layer in neural networks.

Default value for number of hidden neurons in second hidden layer in neural networks.

Default value for number of hidden neurons in second hidden layer in neural networks.

Default value for number of hidden neurons in third hidden layer in neural networks.

Default value for number of hidden neurons in third hidden layer in neural networks.

Default value for number of hidden neurons in third hidden layer in neural networks.

Default value for maximum number of epochs in neural networks.

Default value for number of epochs in bundle in neural networks.

Flag for enabling toelrance that represent a percentage of the output range.

Default value for number of input neurons.

Default value for number of output neurons.

Auxiliary properties for defining tolerances in a relative way:


Property Documentation

double IG::Neural::NeuralTrainingLimits::LearningRateMin [get, set]

Minimum limit for learning rate.

double IG::Neural::NeuralTrainingLimits::LearningRateMax [get, set]

Maximum limit for learning rate.

int IG::Neural::NeuralTrainingLimits::LearningRateNum [get, set]

Number of learning rates.

double IG::Neural::NeuralTrainingLimits::MomentumMin [get, set]

Minimum limit for momentum.

double IG::Neural::NeuralTrainingLimits::MomentumMax [get, set]

Maximum limit for momentum.

int IG::Neural::NeuralTrainingLimits::MomentumNum [get, set]

Number of momentums.

double IG::Neural::NeuralTrainingLimits::AlphaMin [get, set]

Minimum limit for alpha value.

double IG::Neural::NeuralTrainingLimits::AlphaMax [get, set]

Maximum limit for alpha value.

int IG::Neural::NeuralTrainingLimits::AlphaNum [get, set]

Number of alpha value.

double IG::Neural::NeuralTrainingLimits::InputSafetyFactorMin [get, set]

Minimum limit for input safety factor value.

double IG::Neural::NeuralTrainingLimits::InputSafetyFactorMax [get, set]

Maximum limit for input safety factor value.

int IG::Neural::NeuralTrainingLimits::InputSafetyFactorNum [get, set]

Number of input safety factor values.

double IG::Neural::NeuralTrainingLimits::OutputSafetyFactorMin [get, set]

Minimum limit for output safety factor value.

double IG::Neural::NeuralTrainingLimits::OutputSafetyFactorMax [get, set]

Maximum limit for output safety factor value.

int IG::Neural::NeuralTrainingLimits::OutputSafetyFactorNum [get, set]

Number of output safety factor values.

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

Maximum number of epochs performed in training.

int IG::Neural::NeuralTrainingLimits::EpochBundle [get, set]

Number of epochs in boundle.

int IG::Neural::NeuralTrainingLimits::InputLenght [get, set]

Number of input neurons.

int IG::Neural::NeuralTrainingLimits::OutputLength [get, set]

Number of output neurons.

bool IG::Neural::NeuralTrainingLimits::EnableRangeTolerance [get, set]

Flag for enabling toelrance that represent a percentage of the output range.

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

Tolerance for RMS.

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

Maximum tolerance for max. abs. difference.

IVector IG::Neural::NeuralTrainingLimits::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::NeuralTrainingLimits::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::NeuralTrainingLimits::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::NeuralTrainingLimits::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
bool IG::Neural::NeuralTrainingLimits::EnableArchitectureTest [get, set]

Flag for enabling test in architecture of ANN.

int IG::Neural::NeuralTrainingLimits::NumHiddenLayersNum [get, set]

Number of hidden layers in neural network.

int IG::Neural::NeuralTrainingLimits::NumHiddenNeuronsFirstMin [get, set]

Minimum number of hidden neurons in first hidden layer.

int IG::Neural::NeuralTrainingLimits::NumHiddenNeuronsFirstMax [get, set]

Maximum number of hidden neurons in first hidden layer.

int IG::Neural::NeuralTrainingLimits::NumHiddenNeuronsFirstNum [get, set]

Number of hidden neurons in first hidden layer.

int [] IG::Neural::NeuralTrainingLimits::NumHiddenNeuronsFirstValues [get, set]

Values of number of hidden neurons in the first layers that will appear in the table.

Specifying an array of values for the number of hidden neurons in the first layer makes possible to use custom values, not just equidistant values between minimal and maximal value.

If array of values is set, the number of values is set to the length of the array, minimal value is set to its first element and maximal value is set to its last element.

int IG::Neural::NeuralTrainingLimits::NumHiddenNeuronsSecondMin [get, set]

Minimum number of hidden neurons in second hidden layer.

int IG::Neural::NeuralTrainingLimits::NumHiddenNeuronsSecondMax [get, set]

Maximum number of hidden neurons in second hidden layer.

int IG::Neural::NeuralTrainingLimits::NumHiddenNeuronsSecondNum [get, set]

Number of hidden neurons in second hidden layer.

int [] IG::Neural::NeuralTrainingLimits::NumHiddenNeuronsSecondValues [get, set]

Values of number of hidden neurons in the second layers that will appear in the table.

Specifying an array of values for the number of hidden neurons in the second layer makes possible to use custom values, not just equidistant values between minimal and maximal value.

If array of values is set, the number of values is set to the length of the array, minimal value is set to its first element and maximal value is set to its last element.

int IG::Neural::NeuralTrainingLimits::NumHiddenNeuronsThirdMin [get, set]

Minimum number of hidden neurons in third hidden layer.

int IG::Neural::NeuralTrainingLimits::NumHiddenNeuronsThirdMax [get, set]

Maximum number of hidden neurons in third hidden layer.

int IG::Neural::NeuralTrainingLimits::NumHiddenNeuronsThirdNum [get, set]

Number of hidden neurons in third hidden layer.

int [] IG::Neural::NeuralTrainingLimits::NumHiddenNeuronsThirdValues [get, set]

Values of number of hidden neurons in the third layer that will appear in the table.

Specifying an array of values for the number of hidden neurons in the third layer makes possible to use custom values, not just equidistant values between minimal and maximal value.

If the array of values is set, the number of values is set to the length of the array, minimal value is set to its first element and maximal value is set to its last element.


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