DocumentCode
2973041
Title
Genetically designing neuro-controllers for a dynamic system
Author
Dasgupta, Dipankar ; McGregor, Douglas R.
Author_Institution
Dept. of Comput. Sci., Strathclyde Univ., Glasgow, UK
Volume
3
fYear
1993
fDate
25-29 Oct. 1993
Firstpage
2951
Abstract
In this paper, me describes the application of a structured genetic algorithm for integrating the process of design and training neural networks for a specific task. The important feature of this genetic approach is that it can determine the network structures and their weights solely by an evolutionary process. The paper presents some experimental results in the automatic design of neural network based controllers for balancing a typical dynamic (pole-cart) system using this genetic approach.
Keywords
control system synthesis; genetic algorithms; intelligent control; learning (artificial intelligence); neural nets; neurocontrollers; dynamic system control; evolutionary process; network structures; network weights; neural network learning; neurocontrollers; pole-cart system; structured genetic algorithm; Acceleration; Algorithm design and analysis; Automatic control; Biological cells; Control systems; Design optimization; Force control; Genetic algorithms; Network topology; Neural networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN
0-7803-1421-2
Type
conf
DOI
10.1109/IJCNN.1993.714341
Filename
714341
Link To Document