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 contribution | Dynamic systems control and identification using VSC-based learning algorithms for perceptron networks |
---|---|
Original language | Spanish |
Pages (from-to) | 23-34 |
Number of pages | 12 |
Journal | Revista Tecnica de la Facultad de Ingenieria Universidad del Zulia |
Volume | 23 |
Issue number | 1 |
State | Published - Apr 2000 |
Externally published | Yes |
Keywords
- Control
- Identification
- Learning algorithms
- Neural networks
- Variable structure control
ASJC Scopus subject areas
- General Engineering