Control e identificación de sistemas dinámicos utilizando redes neuronales entrenadas con algoritmos basados en control de estructura variable

Translated title of the contribution: Dynamic systems control and identification using VSC-based learning algorithms for perceptron networks

Francklin Rivas-Echeverría, Eliezer Colina-Morles

Research output: Contribution to journalArticlepeer-review

Abstract

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.

Translated title of the contributionDynamic systems control and identification using VSC-based learning algorithms for perceptron networks
Original languageSpanish
Pages (from-to)23-34
Number of pages12
JournalRevista Tecnica de la Facultad de Ingenieria Universidad del Zulia
Volume23
Issue number1
StatePublished - Apr 2000
Externally publishedYes

Keywords

  • Control
  • Identification
  • Learning algorithms
  • Neural networks
  • Variable structure control

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Dynamic systems control and identification using VSC-based learning algorithms for perceptron networks'. Together they form a unique fingerprint.

Cite this