Dynamic systems control and identification using VSC-based learning algorithms for perceptron networks

In this paper a set of Variable Structure Control (VSC)-based on-line learning algorithms for continuous time two layer and three layer perceptron networks with non-linear and linear activation functions are presented. The proposed algorithms result in a temporal learning capabilities of a neural n...

Full description

Bibliographic Details
Main Authors: Francklin Rivas Echeverría, Eliezer Colina Morles
Format: Article
Language:English
Published: Universidad del Zulia 2010-11-01
Series:Revista Técnica de la Facultad de Ingeniería
Subjects:
Online Access:https://www.produccioncientificaluz.org/index.php/tecnica/article/view/5671
_version_ 1811296852486651904
author Francklin Rivas Echeverría
Eliezer Colina Morles
author_facet Francklin Rivas Echeverría
Eliezer Colina Morles
author_sort Francklin Rivas Echeverría
collection DOAJ
description In this paper a set of Variable Structure Control (VSC)-based on-line learning algorithms for continuous time two layer and three layer perceptron networks with non-linear and linear activation functions are presented. The proposed algorithms result in a temporal learning capabilities of a neural network with dynamically adjusted weights, and zero convergence of the learning error in a finite time. These learning algorithms are used with identification and control schemes for linear and non linear dynamic systems.
first_indexed 2024-04-13T05:55:33Z
format Article
id doaj.art-0f0935f29d1d4c98ab9da0bc3c2d1719
institution Directory Open Access Journal
issn 0254-0770
2477-9377
language English
last_indexed 2024-04-13T05:55:33Z
publishDate 2010-11-01
publisher Universidad del Zulia
record_format Article
series Revista Técnica de la Facultad de Ingeniería
spelling doaj.art-0f0935f29d1d4c98ab9da0bc3c2d17192022-12-22T02:59:38ZengUniversidad del ZuliaRevista Técnica de la Facultad de Ingeniería0254-07702477-93772010-11-01231Dynamic systems control and identification using VSC-based learning algorithms for perceptron networksFrancklin Rivas Echeverría0Eliezer Colina Morles1Universidad de Los Andes-VenezuelaUniversidad de Los Andes-Venezuela In this paper a set of Variable Structure Control (VSC)-based on-line learning algorithms for continuous time two layer and three layer perceptron networks with non-linear and linear activation functions are presented. The proposed algorithms result in a temporal learning capabilities of a neural network with dynamically adjusted weights, and zero convergence of the learning error in a finite time. These learning algorithms are used with identification and control schemes for linear and non linear dynamic systems. https://www.produccioncientificaluz.org/index.php/tecnica/article/view/5671neural networksvariable structure controllearning algorithmsidentificationcontrol
spellingShingle Francklin Rivas Echeverría
Eliezer Colina Morles
Dynamic systems control and identification using VSC-based learning algorithms for perceptron networks
Revista Técnica de la Facultad de Ingeniería
neural networks
variable structure control
learning algorithms
identification
control
title Dynamic systems control and identification using VSC-based learning algorithms for perceptron networks
title_full Dynamic systems control and identification using VSC-based learning algorithms for perceptron networks
title_fullStr Dynamic systems control and identification using VSC-based learning algorithms for perceptron networks
title_full_unstemmed Dynamic systems control and identification using VSC-based learning algorithms for perceptron networks
title_short Dynamic systems control and identification using VSC-based learning algorithms for perceptron networks
title_sort dynamic systems control and identification using vsc based learning algorithms for perceptron networks
topic neural networks
variable structure control
learning algorithms
identification
control
url https://www.produccioncientificaluz.org/index.php/tecnica/article/view/5671
work_keys_str_mv AT francklinrivasecheverria dynamicsystemscontrolandidentificationusingvscbasedlearningalgorithmsforperceptronnetworks
AT eliezercolinamorles dynamicsystemscontrolandidentificationusingvscbasedlearningalgorithmsforperceptronnetworks