You are here: Start » AVL.NET » Function Reference » Data Classification » Multilayer Perceptron » AVL.MLP_Init

AVL.MLP_Init

Creates multilayer perceptron model.

Namespace:AvlNet
Assembly:AVL.NET.dll

Syntax

C++
C#
 
public static void MLP_Init
(
	NullableRef<IList<int>> inHiddenLayers,
	AvlNet.ActivationFunction inActivationFunction,
	AvlNet.MlpPreprocessing inPreprocessing,
	int? inRandomSeed,
	int inInputCount,
	int inOutputCount,
	AvlNet.MlpModel outMlpModel
)

Parameters

Name Type Range Default Description
inHiddenLayersAvlNet.NullableRef<System.Collections.Generic.IList<int>>Internal structure of MLP network. Default value: atl::NIL.
inActivationFunctionAvlNet.ActivationFunctionType of activation function used to calculate neural response.
inPreprocessingAvlNet.MlpPreprocessingMethod of processing input data before learning.
inRandomSeedint?<0, INF>Number used as starting random seed. Default value: atl::NIL.
inInputCountint<1, INF>1MLP network input count. Default value: 1.
inOutputCountint<1, INF>1MLP network output count. Default value: 1.
outMlpModelAvlNet.MlpModelInitialized 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.

Function Overrides

See also