DocumentCode
835509
Title
Introduction to neural networks for intelligent control
Author
Bavarian, Behnam
Author_Institution
Robotics Res. Lab., California Univ., Irvine, CA, USA
Volume
8
Issue
2
fYear
1988
fDate
4/1/1988 12:00:00 AM
Firstpage
3
Lastpage
7
Abstract
Neural network architecture is presented as one approach to the design and implementation of intelligent control systems. Neural networks can be considered as massively parallel distributed processing systems with the potential for ever-improving performance through dynamical learning. The nomenclature and characteristics of neural networks are outlined. Two simple examples are presented to illustrate applications to control systems: one is fault isolation mapping, and the other involves optimization of a Hopfield network that defines a clockless analog-to-digital conversion.<>
Keywords
computer architecture; control system synthesis; learning systems; neural nets; parallel processing; Hopfield network; clockless analog-to-digital conversion; control design; dynamical learning; fault isolation mapping; intelligent control; intelligent control systems; massively parallel distributed processing systems; neural network architecture; optimization; Adaptive control; Control systems; Distributed processing; Feedback control; Feedback loop; Intelligent control; Neural networks; Robust control; Sensor systems; Uncertainty;
fLanguage
English
Journal_Title
Control Systems Magazine, IEEE
Publisher
ieee
ISSN
0272-1708
Type
jour
DOI
10.1109/37.1866
Filename
1866
Link To Document