You are here: Start » FIL.NET » Function Reference » Data Classification » Multilayer Perceptron » FIL.MLP_Init
Creates multilayer perceptron model.
Namespace: | FilNet |
---|---|
Assembly: | FIL.NET.dll |
Syntax
C++
C#
public static void MLP_Init ( NullableRef<IList<int>> inHiddenLayers, FilNet.ActivationFunction inActivationFunction, FilNet.MlpPreprocessing inPreprocessing, int? inRandomSeed, int inInputCount, int inOutputCount, FilNet.MlpModel outMlpModel )
Parameters
Name | Type | Range | Default | Description | |
---|---|---|---|---|---|
inHiddenLayers | FilNet.NullableRef<System.Collections.Generic.IList<int>> | Internal structure of MLP network. Default value: ftl::NIL. | |||
inActivationFunction | FilNet.ActivationFunction | Type of activation function used to calculate neural response. | |||
inPreprocessing | FilNet.MlpPreprocessing | Method of processing input data before learning. | |||
inRandomSeed | int? | <0, INF> | Number used as starting random seed. Default value: ftl::NIL. | ||
inInputCount | int | <1, INF> | 1 | MLP network input count. Default value: 1. | |
inOutputCount | int | <1, INF> | 1 | MLP network output count. Default value: 1. | |
outMlpModel | FilNet.MlpModel | Initialized MlpModel. |
Description
Filter initializes and sets structure of the MlpModel.
Image: Internal structure of MlpModel. Function f denotes the inActivationFunction.
Parameter inHiddenLayers represents number of neurons in consecutive hidden layers.
The parameter inActivationFunction is a function used to calculate internal neuron activation.
The weights of the multilayer perceptron are initialized by a random numbers. Their values depend on inRandomSeed value.
Parameters inInputCount and inOutputCount defines network inputs and outputs count.