Plenary
Lecture
Variable Structure-based Learning Algorithms
for Neural Networks
Professor Francklin Rivas-Echeverria
Universidad de Los Andes
Laboratorio de Sistemas Inteligentes (LabSIULA)
Merida, Venezuela
E-mail: rivas@ula.ve
Abstract:
This plenary speech covers Control schemes for nonlinear
dynamical systems using Variable Structure Control (VSC)-based
adaptation algorithms for Neural Networks (NN). The VSC
approach has been used in diverse control applications,
and is new in the NN area. Some of the features of these
algorithms are: Finite time convergence to zero of the
learning error, guaranteed by stability analysis,
robustness with respect to input and external
perturbations and easy for computer implantation.
The presentation includes identification and control
applications in order to illustrate the feasibility of
the approach.
The plenary speech will contemplate the following
topics:
- VSC-based algorithms for a single neuron and for
multilayer NN.
- Dynamical filter-weights Neuron.
- Dynamic NN VSC- based Adaptive Control of a Class of
unknown Nonlinear Systems.
- On-line Identification of a direct and inverse
transfer operator for dynamical systems.
- Inverse model-based Control using NN with VSC-based
adaptation algorithms.
- Model Reference Adaptive Control using a VSC-based
Neuron-like virtual model.
- Further works in the area of VSC-based learning
algorithms applications.
Brief Biography of the Speaker:
Francklin Rivas-Echeverria Systems Engineer, MSc. in
Control Engineering and Applied Science Doctor. Full
professor in Control Systems Department, at Universidad
de Los Andes, Venezuela. He has been invited professor
in the Laboratoire d'Architecture et d'Analyse des
Systemes (LAAS, Toulouse-France) and some Venezuelan and
international Universities. He has also been technical
advisor for “Venezuelan Oil Company” (PDVSA), “Aluminum
Venezuelan Company” (VENALUM), “Steel Venezuelan
Company” (SIDOR), Trolleybus System in Venezuela (TROLMERIDA).
He has created and is the Director of the Intelligent
Systems Laboratory and is the head of the University
consulting unit (UAPIT-ULA). Over 180 publications in
high level conferences and journals: the main topics of
his papers are: Artificial Intelligence, Intelligent
Control, Automation Systems and Industrial Applications.
He has applied his results to many fields: Processes
Control and Supervision, Oil production, Steel
production processes, among others. Also, has developed
several tools for automatic control teaching. He is
coauthor of two books concerning Artificial Intelligence
and Nonlinear Systems.
|