Trajectory tracking with dynamic neural networks

A. Ferit Konar, Y. Becerikli, T. Samad

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Scopus citations

Abstract

The application of artificial neural networks to dynamical systems has been constrained by the non-dynamical nature popular network architectures. Many of the difficulties that ensue - large network sizes, long training times, the need to predetermine buffer lengths - can be overcomed with dynamic neural networks. The minimization of a quadratic performance index is considered for trajectory tracking or process simulation applications. Two approaches for gradient computation are discussed: forward and adjoint sensitivity analysis. The computational complexity of the latter is significantly less, but it requires a backward integration capability. We also discuss two parameter updating methods: gradient descent and a Levenberg-Marquardt approach.

Original languageEnglish (US)
Title of host publicationIEEE International Symposium on Intelligent Control - Proceedings
Editors Anon
PublisherIEEE
Pages173-180
Number of pages8
StatePublished - Jan 1 1997
EventProceedings of the 1997 IEEE International Symposium on Intelligent Control - Istanbul, Turk
Duration: Jul 16 1997Jul 18 1997

Other

OtherProceedings of the 1997 IEEE International Symposium on Intelligent Control
CityIstanbul, Turk
Period7/16/977/18/97

Fingerprint Dive into the research topics of 'Trajectory tracking with dynamic neural networks'. Together they form a unique fingerprint.

Cite this