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

IG::Neural::NeuralTrainingLimitsDto Class Reference

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

List of all members.

Public Member Functions

override NeuralTrainingLimits CreateObject ()
 Creates and returns a new object of the corresponding type.

Public Attributes

double LearningRateMin
 Minimum limit for learning rate.
double LearningRateMax
 Maximum limit for learning rate.
int LearningRateNum
 Number of learning rates.
double MomentumMin
 Minimum limit for momentum.
double MomentumMax
 Maximum limit for momentum.
int MomentumNum
 Number of momentums.
double AlphaMin
 Minimum limit for alpha value.
double AlphaMax
 Maximum limit for alpha value.
int AlphaNum
 Number of alpha values.
double InputSafetyFactorMin
 Minimum limit for input safety factor value.
double InputSafetyFactorMax
 Maximum limit for input safety factor value.
int InputSafetyFactorNum
 Number of input safety factor values.
double OutputSafetyFactorMin
 Minimum limit for output safety factor value.
double OutputSafetyFactorMax
 Maximum limit for output safety factor value.
int OutputSafetyFactorNum
 Number of output safety factor values.
int MaxEpochs
 Maximum number of epochs performed in training.
int EpochBundle
 Number of epochs in boundle.
bool EnableRangeTolerance
 Flag for enabling toelrance that represent a percentage of the output range.
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.
VectorDtoBase ToleranceRmsRelativeToRange
 Relative tolerances on RMS errors of outputs over training points, relative to the correspoinding ranges of output data.
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.
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.
VectorDtoBase ToleranceMaxRelativeToRange
 Relative tolerances on max. abs. errors of outputs over training points, relative to the correspoinding ranges of output data.
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.
int InputLenght
 Number of input neurons.
int OutputLength
 Number of output neurons.
bool EnableArchitectureTest
 Flag for enabling test in architecture of ANN.
int NumHiddenLayersNum
 Number of hidden layers in neural network.
int NumHiddenNeuronsFirstMin
 Minimum number of hidden neurons in first hidden layer.
int NumHiddenNeuronsFirstMax
 Maximum number of hidden neurons in first hidden layer.
int NumHiddenNeuronsFirstNum
 Number of numbers of hidden neurons in first hidden layer.
int[] NumHiddenNeuronsFirstValues
 Values for number of hidden neurons in the first hidden layer.
int NumHiddenNeuronsSecondMin
 Minimum number of hidden neurons in second hidden layer.
int NumHiddenNeuronsSecondMax
 Maximum number of hidden neurons in second hidden layer.
int NumHiddenNeuronsSecondNum
 Number of numbers of hidden neurons in second hidden layer.
int[] NumHiddenNeuronsSecondValues
 Values for number of hidden neurons in the second hidden layer.
int NumHiddenNeuronsThirdMin
 Minimum number of hidden neurons in third hidden layer.
int NumHiddenNeuronsThirdMax
 Maximum number of hidden neurons in third hidden layer.
int NumHiddenNeuronsThirdNum
 Number of numbers of hidden neurons in third hidden layer.
int[] NumHiddenNeuronsThirdValues
 Values for number of hidden neurons in the third hidden layer.

Protected Member Functions

override void CopyFromPlain (NeuralTrainingLimits trainingLimits)
 Copies the specified training limits to the current DTO.
override void CopyToPlain (ref NeuralTrainingLimits trainingLimits)
 Copies contents of the current DTO to the specified training limits object.

Detailed Description

Transfer Object (DTO) for neural network training limits.

$A Tako78 Aug12; Igor Aug12;


Member Function Documentation

override NeuralTrainingLimits IG::Neural::NeuralTrainingLimitsDto::CreateObject ( ) [inline]

Creates and returns a new object of the corresponding type.

override void IG::Neural::NeuralTrainingLimitsDto::CopyFromPlain ( NeuralTrainingLimits  trainingLimits) [inline, protected]

Copies the specified training limits to the current DTO.

Parameters:
trainingLimitsObject that is copied to the current DTO.
override void IG::Neural::NeuralTrainingLimitsDto::CopyToPlain ( ref NeuralTrainingLimits  trainingLimits) [inline, protected]

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

Parameters:
trainingLimitsObject that the current DTO content is copied to.

Member Data Documentation

Minimum limit for learning rate.

Maximum limit for learning rate.

Minimum limit for momentum.

Maximum limit for momentum.

Minimum limit for alpha value.

Maximum limit for alpha value.

Number of alpha values.

Minimum limit for input safety factor value.

Maximum limit for input safety factor value.

Number of input safety factor values.

Minimum limit for output safety factor value.

Maximum limit for output safety factor value.

Number of output safety factor values.

Maximum number of epochs performed in training.

Number of epochs in boundle.

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

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;

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

See also:
NeuralApproximatorBase.ToleranceRmsRelativeToRange

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

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;

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

See also:
NeuralApproximatorBase.ToleranceMaxRelativeToRange

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

Flag for enabling test in architecture of ANN.

Number of hidden layers in neural network.

Minimum number of hidden neurons in first hidden layer.

Maximum number of hidden neurons in first hidden layer.

Number of numbers of hidden neurons in first hidden layer.

Values for number of hidden neurons in the first hidden layer.

Minimum number of hidden neurons in second hidden layer.

Maximum number of hidden neurons in second hidden layer.

Number of numbers of hidden neurons in second hidden layer.

Values for number of hidden neurons in the second hidden layer.

Minimum number of hidden neurons in third hidden layer.

Maximum number of hidden neurons in third hidden layer.

Number of numbers of hidden neurons in third hidden layer.

Values for number of hidden neurons in the third hidden layer.


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