Evolving neurocontrollers using evolutionary programming

Author

Saravanan, N. ; Fogel, D.B.

Author_Institution

Dept. of Mech. Eng., Florida Atlantic Univ., Boca Raton, FL, USA

fYear

1994

fDate

27-29 Jun 1994

Firstpage

217

Abstract

Evolutionary programming (EP) is a stochastic optimization technique that can be used to train neural networks. Unlike many training algorithms, EP does not require gradient information, and this facet increases the applicability of the procedure. The current investigation focuses on evolving neurocontrollers for two difficult nonlinear unstable systems. In the first, two separate poles of varying length are mounted on a cart. In the second, two jointed poles of varying length are mounted on a cart. The objective is to bring the systems into balance. The results indicate the suitability for using EP to evolve neurocontrollers for these two systems

Keywords

adaptive control; genetic algorithms; intelligent control; learning (artificial intelligence); neural nets; nonlinear control systems; optimisation; stability; balance; cart; evolutionary programming; jointed poles; neural network training; neurocontrollers; nonlinear unstable systems; separate poles; stochastic optimization technique; Artificial intelligence; Biological cells; Control systems; Evolutionary computation; Feedforward systems; Genetic algorithms; Genetic mutations; Genetic programming; Neurocontrollers; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the First IEEE Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1899-4

Type

conf

DOI

10.1109/ICEC.1994.350013

Filename

350013