On-line learning of dynamical systems in the presence of model mismatch and disturbances

This paper is concerned with the online learning of unknown dynamical systems using a recurrent neural network. The unknown dynamic systems to be learned are subject to disturbances and possibly unstable. The neural-network model used has a simple architecture with one layer of adaptive connection w...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on neural networks Vol. 11; no. 6; pp. 1272 - 1283
Main Authors: Jiang, D, Wang, J
Format: Journal Article
Language:English
Published: United States IEEE 01.11.2000
Subjects:
Artificial neural networks
Backpropagation algorithms
Computer networks
Convergence
Cost function
Disturbances
Dynamical systems
Dynamics
Errors
Function approximation
Intelligent networks
Learning
Multi-layer neural network
Neural networks
On-line systems
Recurrent neural networks
ISSN:1045-9227
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper is concerned with the online learning of unknown dynamical systems using a recurrent neural network. The unknown dynamic systems to be learned are subject to disturbances and possibly unstable. The neural-network model used has a simple architecture with one layer of adaptive connection weights. Four learning rules are proposed for the cases where the system state is measurable in continuous or discrete time. Some of these learning rules extend the /spl sigma/-modification of the standard gradient learning rule. Convergence properties are given to show that the weight parameters of the recurrent neural network are bounded and the state estimation error converges exponentially to a bounded set, which depends on the modeling error and the disturbance bound. The effectiveness of the proposed learning rules for the recurrent neural network is demonstrated using an illustrative example of tracking a Brownian motion.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:1045-9227
DOI:10.1109/72.883420