NeurApp 1.1
NeurApp - software for exploring approximation by artificial neural networks on functions of one or two variables.
|
Transfer Object (DTO) for neural network training set. More...
Public Member Functions | |
override NeuralTrainingParameters | CreateObject () |
Creates and returns a new object of the corresponding type. | |
Public Attributes | |
double | LearningRate |
Learning rate. | |
double | Momentum |
Momentum. Specifies how much changes of weight in the previous iterations affect changes in the current iterations. | |
double | SigmoidAlphaValue |
Sigmoid alpha value (used in networks with sigmoid activation functions). | |
int | InputLength |
Gets or sets the number of input neurons. | |
int | OutputLength |
Gets or sets the number of output neurons. | |
double | InputBoundSafetyFactor |
double | OutputBoundSafetyFactor |
int | MaxEpochs |
Maximal number of epochs performed in the training procedure. | |
int | 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. | |
VectorDtoBase | InputRange |
Range from actual inputs. | |
VectorDtoBase | OutputRange |
Range from actual outputs. | |
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 | NumHiddenLayers |
Number of Hideden layers. | |
int[] | NumHidenNeurons |
Numbers of neurons in each hidden layer. | |
bool | IsNetworkTrained |
Whether the network is trained (and results exist). | |
VectorDtoBase | ErrorsTrainingRms |
RMS errors calculated on training data. | |
VectorDtoBase[] | ErrorsTrainingRmsTable |
Convergence Table of RMS errors calculated on training data. | |
VectorDtoBase | ErrorsTrainingMax |
Maximal errors calculated on training data. | |
VectorDtoBase[] | ErrorsTrainingMaxTable |
Convergence Table of Maximal errors calculated on training data. | |
VectorDtoBase | ErrorsTrainingMeanAbs |
Mean absolute errors calculated on training data. | |
VectorDtoBase | ErrorsVerificationRms |
RMS errors calculated on verification data. | |
VectorDtoBase[] | ErrorsVerificationRmsTable |
Convergence Table of RMS errors calculated on verification data. | |
VectorDtoBase | ErrorsVerificationMax |
Maximal errors calculated on verification data. | |
VectorDtoBase[] | ErrorsVerificationMaxTable |
Convergence Table of Maximal errors calculated on verification data. | |
VectorDtoBase | ErrorsVerificationMeanAbs |
Maximal errors calculated on training data. | |
List< VectorDtoBase > | ErrorsRmsList |
int | NumEpochs |
Number of epochs actually spent at training. | |
double | TrainingTime |
Time spent for training. | |
double | TrainingCpuTime |
CPU time spent for training. | |
int[] | EpochNumbers |
List of epoch numbers at which convergence data was sampled. | |
double[] | EpochErrorsRms |
List of sampled RMS errors corresponding to epoch numbers from EpochNumbers. | |
double[] | EpochErrorsAbs |
List of sampled absolute errors corresponding to epoch numbers from EpochNumbers. | |
Protected Member Functions | |
override void | CopyFromPlain (NeuralTrainingParameters trainingParameters) |
Copies the specified training parameters to the current DTO. | |
override void | CopyToPlain (ref NeuralTrainingParameters trainingParameters) |
Copies contents of the current DTO to the specified training parameters object. |
Transfer Object (DTO) for neural network training set.
$A Igor Jun12; Tako78 Jun12;
override NeuralTrainingParameters IG::Neural::NeuralTrainingParametersDto::CreateObject | ( | ) | [inline] |
Creates and returns a new object of the corresponding type.
override void IG::Neural::NeuralTrainingParametersDto::CopyFromPlain | ( | NeuralTrainingParameters | trainingParameters | ) | [inline, protected] |
Copies the specified training parameters to the current DTO.
trainingParameters | Object that is copied to the current DTO. |
override void IG::Neural::NeuralTrainingParametersDto::CopyToPlain | ( | ref NeuralTrainingParameters | trainingParameters | ) | [inline, protected] |
Copies contents of the current DTO to the specified training parameters object.
trainingParameters | Object that the current DTO content is copied to. |
Learning rate.
Momentum. Specifies how much changes of weight in the previous iterations affect changes in the current iterations.
Sigmoid alpha value (used in networks with sigmoid activation functions).
Gets or sets the number of input neurons.
Gets or sets the number of output neurons.
Maximal number of epochs performed in the training procedure.
$A Tako78 Jul12;
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::Neural::NeuralTrainingParametersDto::InputRange |
Range from actual inputs.
$A Tako78 Octl12;
VectorDtoBase IG::Neural::NeuralTrainingParametersDto::OutputRange |
Range from actual outputs.
$A Tako78 Octl12;
VectorDtoBase IG::Neural::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;
Relative tolerances on RMS errors of outputs over training points, relative to the correspoinding ranges of output data.
double IG::Neural::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.
VectorDtoBase IG::Neural::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;
Relative tolerances on max. abs. errors of outputs over training points, relative to the correspoinding ranges of output data.
double IG::Neural::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.
Number of Hideden layers.
$A Tako78 Jul12;
Numbers of neurons in each hidden layer.
$A Tako78 Jul12;
Whether the network is trained (and results exist).
$A Tako78 Jul12;
RMS errors calculated on training data.
$A Tako78 Jul12;
VectorDtoBase [] IG::Neural::NeuralTrainingParametersDto::ErrorsTrainingRmsTable |
Convergence Table of RMS errors calculated on training data.
$A Tako78 Aug12;
Maximal errors calculated on training data.
$A Tako78 Jul12;
VectorDtoBase [] IG::Neural::NeuralTrainingParametersDto::ErrorsTrainingMaxTable |
Convergence Table of Maximal errors calculated on training data.
$A Tako78 Aug12;
Mean absolute errors calculated on training data.
$A Tako78 Jul12;
RMS errors calculated on verification data.
$A Tako78 Jul12;
VectorDtoBase [] IG::Neural::NeuralTrainingParametersDto::ErrorsVerificationRmsTable |
Convergence Table of RMS errors calculated on verification data.
$A Tako78 Aug12;
Maximal errors calculated on verification data.
$A Tako78 Jul12;
VectorDtoBase [] IG::Neural::NeuralTrainingParametersDto::ErrorsVerificationMaxTable |
Convergence Table of Maximal errors calculated on verification data.
$A Tako78 Aug12;
Maximal errors calculated on training data.
$A Tako78 Jul12;
List<VectorDtoBase> IG::Neural::NeuralTrainingParametersDto::ErrorsRmsList |
Number of epochs actually spent at training.
$A Tako78 Jul12;
Time spent for training.
$A Tako78 Jul12;;
CPU time spent for training.
$A Tako78 Jul12;
List of epoch numbers at which convergence data was sampled.
List of sampled RMS errors corresponding to epoch numbers from EpochNumbers.
List of sampled absolute errors corresponding to epoch numbers from EpochNumbers.