Back to Adaptive Vision Library website
You are here: Start » Function Reference » Multilayer Perceptron » MLP_Init
MLP_Init
Creates multilayer perceptron model.
Header: | AVL.h |
---|
Syntax
C++
C#
void avl::MLP_Init ( atl::Optional<const atl::Array<int>&> inHiddenLayers, avl::ActivationFunction::Type inActivationFunction, avl::MlpPreprocessing::Type inPreprocessing, atl::Optional<int> inRandomSeed, int inInputCount, int inOutputCount, avl::MlpModel& outMlpModel )
Parameters
Name | Type | Range | Default | Description | |
---|---|---|---|---|---|
inHiddenLayers | Optional<const Array<int>&> | NIL | Internal structure of MLP network | ||
inActivationFunction | ActivationFunction::Type | Type of activation function used to calculate neural response | |||
inPreprocessing | MlpPreprocessing::Type | Method of processing input data before learning | |||
inRandomSeed | Optional<int> | 0 - | NIL | Number used as starting random seed | |
inInputCount | int | 1 - | 1 | MLP network input count | |
inOutputCount | int | 1 - | 1 | MLP network output count | |
outMlpModel | 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.
See Also
- MLP_Respond – Calculates multilayer perceptron answer.
- MLP_Train – Creates and trains multilayer perceptron classifier.