New switched filtering method for recurrent neural networks

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

Abstract

In this paper, we propose a new robust filtering method for switched neural networks via input/output-to-state stability (IOSS) approach. This robust filtering method guarantees that the filtering error system is asymptotically stable and input/output-to-state stable for the external disturbance. The unknown gain matrix of the proposed filter can be obtained by solving a set of linear matrix inequalities (LMIs), which can be easily facilitated by using some standard numerical packages.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011
Pages71-74
Number of pages4
Volume1
DOIs
Publication statusPublished - 2011 Sep 28
Externally publishedYes
Event2011 International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011 - Bali, Indonesia
Duration: 2011 Aug 42011 Aug 7

Other

Other2011 International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011
CountryIndonesia
CityBali
Period11/8/411/8/7

Fingerprint

Recurrent neural networks
Linear matrix inequalities
Neural networks

Keywords

  • input/output-to-state stability
  • robust filtering
  • switched neural networks

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Computational Theory and Mathematics

Cite this

Ahn, C. K. (2011). New switched filtering method for recurrent neural networks. In Proceedings of the International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011 (Vol. 1, pp. 71-74). [6007842] https://doi.org/10.1109/URKE.2011.6007842

New switched filtering method for recurrent neural networks. / Ahn, Choon Ki.

Proceedings of the International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011. Vol. 1 2011. p. 71-74 6007842.

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

Ahn, CK 2011, New switched filtering method for recurrent neural networks. in Proceedings of the International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011. vol. 1, 6007842, pp. 71-74, 2011 International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011, Bali, Indonesia, 11/8/4. https://doi.org/10.1109/URKE.2011.6007842
Ahn CK. New switched filtering method for recurrent neural networks. In Proceedings of the International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011. Vol. 1. 2011. p. 71-74. 6007842 https://doi.org/10.1109/URKE.2011.6007842
Ahn, Choon Ki. / New switched filtering method for recurrent neural networks. Proceedings of the International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011. Vol. 1 2011. pp. 71-74
@inproceedings{e20bc88183ef45fa9c49daa6fb2be0bc,
title = "New switched filtering method for recurrent neural networks",
abstract = "In this paper, we propose a new robust filtering method for switched neural networks via input/output-to-state stability (IOSS) approach. This robust filtering method guarantees that the filtering error system is asymptotically stable and input/output-to-state stable for the external disturbance. The unknown gain matrix of the proposed filter can be obtained by solving a set of linear matrix inequalities (LMIs), which can be easily facilitated by using some standard numerical packages.",
keywords = "input/output-to-state stability, robust filtering, switched neural networks",
author = "Ahn, {Choon Ki}",
year = "2011",
month = "9",
day = "28",
doi = "10.1109/URKE.2011.6007842",
language = "English",
isbn = "9781424499830",
volume = "1",
pages = "71--74",
booktitle = "Proceedings of the International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011",

}

TY - GEN

T1 - New switched filtering method for recurrent neural networks

AU - Ahn, Choon Ki

PY - 2011/9/28

Y1 - 2011/9/28

N2 - In this paper, we propose a new robust filtering method for switched neural networks via input/output-to-state stability (IOSS) approach. This robust filtering method guarantees that the filtering error system is asymptotically stable and input/output-to-state stable for the external disturbance. The unknown gain matrix of the proposed filter can be obtained by solving a set of linear matrix inequalities (LMIs), which can be easily facilitated by using some standard numerical packages.

AB - In this paper, we propose a new robust filtering method for switched neural networks via input/output-to-state stability (IOSS) approach. This robust filtering method guarantees that the filtering error system is asymptotically stable and input/output-to-state stable for the external disturbance. The unknown gain matrix of the proposed filter can be obtained by solving a set of linear matrix inequalities (LMIs), which can be easily facilitated by using some standard numerical packages.

KW - input/output-to-state stability

KW - robust filtering

KW - switched neural networks

UR - http://www.scopus.com/inward/record.url?scp=80053117946&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053117946&partnerID=8YFLogxK

U2 - 10.1109/URKE.2011.6007842

DO - 10.1109/URKE.2011.6007842

M3 - Conference contribution

AN - SCOPUS:80053117946

SN - 9781424499830

VL - 1

SP - 71

EP - 74

BT - Proceedings of the International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011

ER -