IGLib 1.4
The IGLib base library for development of numerical, technical and business applications.
|
Base comparer class (implementation of the IComparer<NeuralTrainingParameters> interface) for conmparing objects of type NeuralTrainingParameters More...
Protected Member Functions | |
double | OutputNorm (IVector vec) |
Protected Attributes | |
IVector | _outputScalingLengths |
bool | _compareMinError = false |
int | _numLastErrors = 1 |
int | _numBundles = 0 |
bool | _compareByTrainingRmsError = true |
bool | _compareByTrainingMaxError = false |
bool | _compareByVerificationRmsError = false |
bool | _compareByVerificationMaxError = false |
Properties | |
IVector | OutputScalingLengths [get, set] |
Vector of scaling lengths for calculation of weighted norms. | |
bool | CompareMinError [get, set] |
Whether the min error in convergence table is used for comparison when errors are compared. If false then mean value of last errors is used. | |
int | NumLastErrors [get, set] |
Number of last errors in convergence list for calculataing the mean value of error. The default valeu is 1 which represent the last error in the converhence list. | |
int | NumBundles [get, set] |
Number of bundles where sorting of convergences stars. The default valeu is 0 which represent normal sorting after the training is done. | |
bool | CompareByTrainingRmsError [get, set] |
Whether training RMS errors from convergence tavble are compared. | |
bool | CompareByTrainingMaxError [get, set] |
Whether Maximal absolute training errors from convergence tavble are compared. | |
bool | CompareByVerificationRmsError [get, set] |
Whether verification RMS errors from convergence tavble are compared. | |
bool | CompareByVerificationMaxError [get, set] |
Whether Maximal absolute verification errors from convergence tavble are compared. | |
Private Member Functions | |
int IComparer < NeuralTrainingParameters >. | Compare (NeuralTrainingParameters a, NeuralTrainingParameters b) |
Base comparer class (implementation of the IComparer<NeuralTrainingParameters> interface) for conmparing objects of type NeuralTrainingParameters
double IG::Neural::NeuralTrainingParameters::ComparerBase::OutputNorm | ( | IVector | vec | ) | [inline, protected] |
int IComparer<NeuralTrainingParameters>. IG::Neural::NeuralTrainingParameters::ComparerBase::Compare | ( | NeuralTrainingParameters | a, |
NeuralTrainingParameters | b | ||
) | [inline, private] |
bool IG::Neural::NeuralTrainingParameters::ComparerBase::_compareMinError = false [protected] |
int IG::Neural::NeuralTrainingParameters::ComparerBase::_numLastErrors = 1 [protected] |
int IG::Neural::NeuralTrainingParameters::ComparerBase::_numBundles = 0 [protected] |
bool IG::Neural::NeuralTrainingParameters::ComparerBase::_compareByTrainingRmsError = true [protected] |
bool IG::Neural::NeuralTrainingParameters::ComparerBase::_compareByTrainingMaxError = false [protected] |
bool IG::Neural::NeuralTrainingParameters::ComparerBase::_compareByVerificationRmsError = false [protected] |
bool IG::Neural::NeuralTrainingParameters::ComparerBase::_compareByVerificationMaxError = false [protected] |
IVector IG::Neural::NeuralTrainingParameters::ComparerBase::OutputScalingLengths [get, set] |
Vector of scaling lengths for calculation of weighted norms.
bool IG::Neural::NeuralTrainingParameters::ComparerBase::CompareMinError [get, set] |
Whether the min error in convergence table is used for comparison when errors are compared. If false then mean value of last errors is used.
int IG::Neural::NeuralTrainingParameters::ComparerBase::NumLastErrors [get, set] |
Number of last errors in convergence list for calculataing the mean value of error. The default valeu is 1 which represent the last error in the converhence list.
int IG::Neural::NeuralTrainingParameters::ComparerBase::NumBundles [get, set] |
Number of bundles where sorting of convergences stars. The default valeu is 0 which represent normal sorting after the training is done.
bool IG::Neural::NeuralTrainingParameters::ComparerBase::CompareByTrainingRmsError [get, set] |
Whether training RMS errors from convergence tavble are compared.
bool IG::Neural::NeuralTrainingParameters::ComparerBase::CompareByTrainingMaxError [get, set] |
Whether Maximal absolute training errors from convergence tavble are compared.
bool IG::Neural::NeuralTrainingParameters::ComparerBase::CompareByVerificationRmsError [get, set] |
Whether verification RMS errors from convergence tavble are compared.
bool IG::Neural::NeuralTrainingParameters::ComparerBase::CompareByVerificationMaxError [get, set] |
Whether Maximal absolute verification errors from convergence tavble are compared.