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

  • Francklin Rivas Echeverría Universidad de Los Andes-Venezuela
  • Eliezer Colina Morles Universidad de Los Andes-Venezuela
Palabras clave: neural networks, variable structure control, learning algorithms, identification, control

Resumen

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.

Descargas

La descarga de datos todavía no está disponible.
Cómo citar
Rivas Echeverría, F. y Colina Morles, E. (1) «Dynamic systems control and identification using VSC-based learning algorithms for perceptron networks», Revista Técnica de la Facultad de Ingeniería. Universidad del Zulia, 23(1). Disponible en: https://produccioncientificaluz.org/index.php/tecnica/article/view/5671 (Accedido: 29marzo2024).
Sección
Artículos de Actualización