37,8K download
Aggiornato 6 mag 2024

simulink-adaptive-neural-networks-library

Simulink® blocks implementing adaptive neural networks

View smxl on File Exchange

Open in MATLAB Online

The adaptive Neural Network Library (MATLAB® 5.3.1 and later) is a collection of blocks that implement several Adaptive Neural Networks featuring different adaptation algorithms.

It was developed mainly in June-July 2001 by Giampiero Campa (West Virginia University) and Mario Fravolini (Perugia University). Later improvements were partially supported by the NASA Grant NCC5-685.

-) There are blocks that implement basically these kinds of neural networks: -) Adaptive Linear Networks (ADALINE) -) Multilayer Layer Perceptron Networks -) Generalized Radial Basis Functions Networks -) Dynamic Cell Structure (DCS) Networks with gaussian or conical basis functions

Also, a Simulink example regarding the approximation of a scalar nonlinear function is included.

Finally, the folder "training" includes step by step instrucions on how to train the GRBF network and the supporting example.

CONTENTS:


ann.mdl - adaptive neural network library anndemo.mdl - demo file

contents.m - info file for the Matlab Help and Ver commands info.xml - info file for the Matlab Start Menu demos.m - info file for the Matlab Demos Menu

emran8.dll - dll file for grbf network dcsgl2.dll - dll file for the gdcs network vrmult.dll - dll file for real matrices multiplication

source - folder containing source code training - folder containing example on grbf training


INSTALLATION:

Unzip the file in a folder of choice, usually under the "toolbox" folder under the Matlab main installation folder.

From MATLAB®, open the "Set Path" interface from the "File" menu, and use the "Add with Subfolders" feature to add the new folder to the matlab path. Then Save and exit the Set Path dialog box.


HOW TO USE THE LIBRARY:

From MATLAB, use the command "ann" to open the library, and double click on the "ann demo" block to open the main demo. This should open a simulink scheme capable of running "out of the box" with any matlab version from R11 to R2007a, that is from Matlab 5.3 to 7.4.

To use the library blocks, just drag and drop them into any simulink scheme. The folder "training" contains instructions on how to train the GRBF network.


ACKNOWLEDGMENTS:

Partial support for the latter development phases of this library was given by the NASA Grant # NCC5-685


G.Campa, West Virginia University, October 2007

Cita come

Giampiero Campa (2024). ANN (https://github.com/giampy1969/simulink-adaptive-neural-networks-library/releases/tag/v1.2), GitHub. Recuperato .

Compatibilità della release di MATLAB
Creato con R11.1
Compatibile con qualsiasi release
Compatibilità della piattaforma
Windows macOS Linux
Categorie
Scopri di più su Sequence and Numeric Feature Data Workflows in Help Center e MATLAB Answers

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Versione Pubblicato Note della release
1.2

See release notes for this release on GitHub: https://github.com/giampy1969/simulink-adaptive-neural-networks-library/releases/tag/v1.2

1.1

See release notes for this release on GitHub: https://github.com/giampy1969/simulink-adaptive-neural-networks-library/releases/tag/v1.1

1.0.0.0

Replaced an older version of training.zip that was mistakenly reintroduced in October 2007. Now everything works out of the box. Please let me know of any more problems.

Per visualizzare o segnalare problemi su questo componente aggiuntivo di GitHub, visita GitHub Repository.
Per visualizzare o segnalare problemi su questo componente aggiuntivo di GitHub, visita GitHub Repository.