Upper Bounds for Approximation of Continuous-Time Dynamics Using Delayed Outputs and Feedforward Neural Networks

Eugene Lavretsky, Naira Hovakimyan, Anthony J. Calise

Research output: Contribution to journalArticlepeer-review

Abstract

The problem of approximation of unknown dynamics of a continuous-time observable nonlinear system is considered using a feedforward neural network, operating over delayed sampled outputs of the system. Error bounds are derived that explicitly depend upon the sampling time interval and network architecture. The main result of this note broadens the class of nonlinear dynamical systems for which adaptive output feedback control and state estimation problems are solvable.

Original languageEnglish (US)
Pages (from-to)1606-1610
Number of pages5
JournalIEEE Transactions on Automatic Control
Volume48
Issue number9
DOIs
StatePublished - Sep 2003
Externally publishedYes

Keywords

  • Adaptive estimation
  • Adaptive output feedback
  • Approximation
  • Continuous-time dynamics
  • Feedforward neural networks

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Upper Bounds for Approximation of Continuous-Time Dynamics Using Delayed Outputs and Feedforward Neural Networks'. Together they form a unique fingerprint.

Cite this