You are here: Start » FIL.NET » FIS.TrainOrganicModel Method
FIS.TrainOrganicModel Method
Trains OrganicModel, which has to be previously initialized with LoadOrganicTrainingData.
| Namespace: | FilNet |
|---|---|
| Assembly: | FIL.NET.dll |
Syntax
public static void TrainOrganicModel ( int inIterationCount, float inLearningRate, float inMomentum, int inModelCapacity, FilNet.DataPreprocessing inPreprocessing, float? inVarianceToLeave, FilNet.OrganicModel ioOrganicModel )
Parameters
| Name | Type | Range | Default | Description | |
|---|---|---|---|---|---|
 | inIterationCount | int | 500 | Number of iteration of internal learning process. Default value: 500. | |
| inLearningRate | float | 0.1f | How aggressive the learning should be. Default value: 0.1f. | |
| inMomentum | float | 0.1f | Factor that helps to move out of local minima. Default value: 0.1f. | |
| inModelCapacity | int | 10 | Internal size of model. Default value: 10. | |
| inPreprocessing | FilNet.DataPreprocessing | Method of cleaning the data before learning. | ||
| inVarianceToLeave | float? | <0.0f, 1.0f> | 0.99f | Value of variance to leave, when PCA preprocessing is done. Default value: 0.99f. |
| ioOrganicModel | FilNet.OrganicModel | Resulting model. |
