Multiple radial basis function networks in modeling and control

Hussein M. Youssef, Jyh Ching Juang

Research output: Contribution to conferencePaper

Abstract

A blending of radial basis function networks and general regression neural networks is proposed and shown to be suitable for the modeling and control of dynamical systems. In this blended scheme, the radial basis function networks account for long term and global dynamics, while the general regression neural networks govern short term and local dynamics. Due to the similarity between radial basis function networks and general regression neural networks, which are both synthesized using Gaussian nodes, the blended scheme can be congruently implemented as a multiple radial basis function network. Training techniques of the two constituting networks are explored in the multiple radial basis function networks so as to achieve a balance in temporal as well as spatial characterization. This leads to a high precision, highly dynamical neural network system. Applications of this multiple radial basis function network in aircraft modeling and control are conducted. Real-time training and precision enhancement are demonstrated.

Original languageEnglish
Pages285-293
Number of pages9
Publication statusPublished - 1993 Jan 1
EventGuidance, Navigation and Control Conference, 1993 - Monterey, United States
Duration: 1993 Aug 91993 Aug 11

Other

OtherGuidance, Navigation and Control Conference, 1993
CountryUnited States
CityMonterey
Period93-08-0993-08-11

Fingerprint

Radial basis function networks
Neural networks
Dynamical systems
Aircraft

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Control and Systems Engineering

Cite this

Youssef, H. M., & Juang, J. C. (1993). Multiple radial basis function networks in modeling and control. 285-293. Paper presented at Guidance, Navigation and Control Conference, 1993, Monterey, United States.
Youssef, Hussein M. ; Juang, Jyh Ching. / Multiple radial basis function networks in modeling and control. Paper presented at Guidance, Navigation and Control Conference, 1993, Monterey, United States.9 p.
@conference{cb2fd98b828f4bddac7cf4585b83fd10,
title = "Multiple radial basis function networks in modeling and control",
abstract = "A blending of radial basis function networks and general regression neural networks is proposed and shown to be suitable for the modeling and control of dynamical systems. In this blended scheme, the radial basis function networks account for long term and global dynamics, while the general regression neural networks govern short term and local dynamics. Due to the similarity between radial basis function networks and general regression neural networks, which are both synthesized using Gaussian nodes, the blended scheme can be congruently implemented as a multiple radial basis function network. Training techniques of the two constituting networks are explored in the multiple radial basis function networks so as to achieve a balance in temporal as well as spatial characterization. This leads to a high precision, highly dynamical neural network system. Applications of this multiple radial basis function network in aircraft modeling and control are conducted. Real-time training and precision enhancement are demonstrated.",
author = "Youssef, {Hussein M.} and Juang, {Jyh Ching}",
year = "1993",
month = "1",
day = "1",
language = "English",
pages = "285--293",
note = "Guidance, Navigation and Control Conference, 1993 ; Conference date: 09-08-1993 Through 11-08-1993",

}

Youssef, HM & Juang, JC 1993, 'Multiple radial basis function networks in modeling and control', Paper presented at Guidance, Navigation and Control Conference, 1993, Monterey, United States, 93-08-09 - 93-08-11 pp. 285-293.

Multiple radial basis function networks in modeling and control. / Youssef, Hussein M.; Juang, Jyh Ching.

1993. 285-293 Paper presented at Guidance, Navigation and Control Conference, 1993, Monterey, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Multiple radial basis function networks in modeling and control

AU - Youssef, Hussein M.

AU - Juang, Jyh Ching

PY - 1993/1/1

Y1 - 1993/1/1

N2 - A blending of radial basis function networks and general regression neural networks is proposed and shown to be suitable for the modeling and control of dynamical systems. In this blended scheme, the radial basis function networks account for long term and global dynamics, while the general regression neural networks govern short term and local dynamics. Due to the similarity between radial basis function networks and general regression neural networks, which are both synthesized using Gaussian nodes, the blended scheme can be congruently implemented as a multiple radial basis function network. Training techniques of the two constituting networks are explored in the multiple radial basis function networks so as to achieve a balance in temporal as well as spatial characterization. This leads to a high precision, highly dynamical neural network system. Applications of this multiple radial basis function network in aircraft modeling and control are conducted. Real-time training and precision enhancement are demonstrated.

AB - A blending of radial basis function networks and general regression neural networks is proposed and shown to be suitable for the modeling and control of dynamical systems. In this blended scheme, the radial basis function networks account for long term and global dynamics, while the general regression neural networks govern short term and local dynamics. Due to the similarity between radial basis function networks and general regression neural networks, which are both synthesized using Gaussian nodes, the blended scheme can be congruently implemented as a multiple radial basis function network. Training techniques of the two constituting networks are explored in the multiple radial basis function networks so as to achieve a balance in temporal as well as spatial characterization. This leads to a high precision, highly dynamical neural network system. Applications of this multiple radial basis function network in aircraft modeling and control are conducted. Real-time training and precision enhancement are demonstrated.

UR - http://www.scopus.com/inward/record.url?scp=84992428203&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992428203&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84992428203

SP - 285

EP - 293

ER -

Youssef HM, Juang JC. Multiple radial basis function networks in modeling and control. 1993. Paper presented at Guidance, Navigation and Control Conference, 1993, Monterey, United States.