Feedback analysis of radial basis functions neural networks via small gain theorem

S. Saad Azhar Ali, Muhammad Shafiq, Jamil M. Ba-Khashwain, Fouad M. Al-Sunni

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

Abstract

Radial basis function neural networks are used in a variety of applications such as pattern recognition, nonlinear identification, control, time series prediction, etc. In this paper, feedback analysis of the learning algorithm of radial basis function neural networks is presented. It studies the robustness of the learning algorithm in the presence of uncertainties that might be due to noisy perturbations at the input or to modeling mismatch. The learning scheme is first associated with a feedback structure and then the stability of that feedback structure is analyzed via small gain theorem. The analysis suggests bounds on the learning rate in order to guarantee that the learning algorithm will behave as robust nonlinear filters and optimal choices for faster convergence speeds.

Original languageEnglish
Title of host publicationIFAC Proceedings Volumes (IFAC-PapersOnline)
Volume17
Edition1 PART 1
DOIs
Publication statusPublished - 2008
Event17th World Congress, International Federation of Automatic Control, IFAC - Seoul, Korea, Republic of
Duration: Jul 6 2008Jul 11 2008

Other

Other17th World Congress, International Federation of Automatic Control, IFAC
CountryKorea, Republic of
CitySeoul
Period7/6/087/11/08

Fingerprint

Learning algorithms
Neural networks
Feedback
Pattern recognition
Time series
Uncertainty

Keywords

  • Closed loop identification
  • Identification for control
  • Nonlinear system identification

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Ali, S. S. A., Shafiq, M., Ba-Khashwain, J. M., & Al-Sunni, F. M. (2008). Feedback analysis of radial basis functions neural networks via small gain theorem. In IFAC Proceedings Volumes (IFAC-PapersOnline) (1 PART 1 ed., Vol. 17) https://doi.org/10.3182/20080706-5-KR-1001.1686

Feedback analysis of radial basis functions neural networks via small gain theorem. / Ali, S. Saad Azhar; Shafiq, Muhammad; Ba-Khashwain, Jamil M.; Al-Sunni, Fouad M.

IFAC Proceedings Volumes (IFAC-PapersOnline). Vol. 17 1 PART 1. ed. 2008.

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

Ali, SSA, Shafiq, M, Ba-Khashwain, JM & Al-Sunni, FM 2008, Feedback analysis of radial basis functions neural networks via small gain theorem. in IFAC Proceedings Volumes (IFAC-PapersOnline). 1 PART 1 edn, vol. 17, 17th World Congress, International Federation of Automatic Control, IFAC, Seoul, Korea, Republic of, 7/6/08. https://doi.org/10.3182/20080706-5-KR-1001.1686
Ali SSA, Shafiq M, Ba-Khashwain JM, Al-Sunni FM. Feedback analysis of radial basis functions neural networks via small gain theorem. In IFAC Proceedings Volumes (IFAC-PapersOnline). 1 PART 1 ed. Vol. 17. 2008 https://doi.org/10.3182/20080706-5-KR-1001.1686
Ali, S. Saad Azhar ; Shafiq, Muhammad ; Ba-Khashwain, Jamil M. ; Al-Sunni, Fouad M. / Feedback analysis of radial basis functions neural networks via small gain theorem. IFAC Proceedings Volumes (IFAC-PapersOnline). Vol. 17 1 PART 1. ed. 2008.
@inproceedings{5f01966fff7f467c92096e08cb7dc295,
title = "Feedback analysis of radial basis functions neural networks via small gain theorem",
abstract = "Radial basis function neural networks are used in a variety of applications such as pattern recognition, nonlinear identification, control, time series prediction, etc. In this paper, feedback analysis of the learning algorithm of radial basis function neural networks is presented. It studies the robustness of the learning algorithm in the presence of uncertainties that might be due to noisy perturbations at the input or to modeling mismatch. The learning scheme is first associated with a feedback structure and then the stability of that feedback structure is analyzed via small gain theorem. The analysis suggests bounds on the learning rate in order to guarantee that the learning algorithm will behave as robust nonlinear filters and optimal choices for faster convergence speeds.",
keywords = "Closed loop identification, Identification for control, Nonlinear system identification",
author = "Ali, {S. Saad Azhar} and Muhammad Shafiq and Ba-Khashwain, {Jamil M.} and Al-Sunni, {Fouad M.}",
year = "2008",
doi = "10.3182/20080706-5-KR-1001.1686",
language = "English",
isbn = "9783902661005",
volume = "17",
booktitle = "IFAC Proceedings Volumes (IFAC-PapersOnline)",
edition = "1 PART 1",

}

TY - GEN

T1 - Feedback analysis of radial basis functions neural networks via small gain theorem

AU - Ali, S. Saad Azhar

AU - Shafiq, Muhammad

AU - Ba-Khashwain, Jamil M.

AU - Al-Sunni, Fouad M.

PY - 2008

Y1 - 2008

N2 - Radial basis function neural networks are used in a variety of applications such as pattern recognition, nonlinear identification, control, time series prediction, etc. In this paper, feedback analysis of the learning algorithm of radial basis function neural networks is presented. It studies the robustness of the learning algorithm in the presence of uncertainties that might be due to noisy perturbations at the input or to modeling mismatch. The learning scheme is first associated with a feedback structure and then the stability of that feedback structure is analyzed via small gain theorem. The analysis suggests bounds on the learning rate in order to guarantee that the learning algorithm will behave as robust nonlinear filters and optimal choices for faster convergence speeds.

AB - Radial basis function neural networks are used in a variety of applications such as pattern recognition, nonlinear identification, control, time series prediction, etc. In this paper, feedback analysis of the learning algorithm of radial basis function neural networks is presented. It studies the robustness of the learning algorithm in the presence of uncertainties that might be due to noisy perturbations at the input or to modeling mismatch. The learning scheme is first associated with a feedback structure and then the stability of that feedback structure is analyzed via small gain theorem. The analysis suggests bounds on the learning rate in order to guarantee that the learning algorithm will behave as robust nonlinear filters and optimal choices for faster convergence speeds.

KW - Closed loop identification

KW - Identification for control

KW - Nonlinear system identification

UR - http://www.scopus.com/inward/record.url?scp=79961018079&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79961018079&partnerID=8YFLogxK

U2 - 10.3182/20080706-5-KR-1001.1686

DO - 10.3182/20080706-5-KR-1001.1686

M3 - Conference contribution

AN - SCOPUS:79961018079

SN - 9783902661005

VL - 17

BT - IFAC Proceedings Volumes (IFAC-PapersOnline)

ER -