Long-short term memory neural network stability and stabilization using linear matrix inequalities

Shankar A. Deka, Dusan M Stipanovic, Boris Murmann, Claire J. Tomlin

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

Abstract

A global asymptotic stability condition for Long Short-Term Memory neural networks is presented in this paper. A linear matrix inequality optimization problem is used to describe this global stability condition. The linear matrix inequality formulation can be viewed as a way for stabilization of Long Short-Term Memory neural networks since the networks' weight matrices and biases can be essentially treated as control variables. The condition and how to compute numerical values for the weight matrices and biases are illustrated by some examples.

Original languageEnglish (US)
Title of host publication2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728103976
DOIs
StatePublished - Jan 1 2019
Event2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Sapporo, Japan
Duration: May 26 2019May 29 2019

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2019-May
ISSN (Print)0271-4310

Conference

Conference2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019
CountryJapan
CitySapporo
Period5/26/195/29/19

Fingerprint

Linear matrix inequalities
Stabilization
Neural networks
Asymptotic stability
Long short-term memory

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Deka, S. A., Stipanovic, D. M., Murmann, B., & Tomlin, C. J. (2019). Long-short term memory neural network stability and stabilization using linear matrix inequalities. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings [8702629] (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS.2019.8702629

Long-short term memory neural network stability and stabilization using linear matrix inequalities. / Deka, Shankar A.; Stipanovic, Dusan M; Murmann, Boris; Tomlin, Claire J.

2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8702629 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May).

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

Deka, SA, Stipanovic, DM, Murmann, B & Tomlin, CJ 2019, Long-short term memory neural network stability and stabilization using linear matrix inequalities. in 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings., 8702629, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019, Sapporo, Japan, 5/26/19. https://doi.org/10.1109/ISCAS.2019.8702629
Deka SA, Stipanovic DM, Murmann B, Tomlin CJ. Long-short term memory neural network stability and stabilization using linear matrix inequalities. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8702629. (Proceedings - IEEE International Symposium on Circuits and Systems). https://doi.org/10.1109/ISCAS.2019.8702629
Deka, Shankar A. ; Stipanovic, Dusan M ; Murmann, Boris ; Tomlin, Claire J. / Long-short term memory neural network stability and stabilization using linear matrix inequalities. 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - IEEE International Symposium on Circuits and Systems).
@inproceedings{e1486356809b417eb91c2db1caa06e12,
title = "Long-short term memory neural network stability and stabilization using linear matrix inequalities",
abstract = "A global asymptotic stability condition for Long Short-Term Memory neural networks is presented in this paper. A linear matrix inequality optimization problem is used to describe this global stability condition. The linear matrix inequality formulation can be viewed as a way for stabilization of Long Short-Term Memory neural networks since the networks' weight matrices and biases can be essentially treated as control variables. The condition and how to compute numerical values for the weight matrices and biases are illustrated by some examples.",
author = "Deka, {Shankar A.} and Stipanovic, {Dusan M} and Boris Murmann and Tomlin, {Claire J.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ISCAS.2019.8702629",
language = "English (US)",
series = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings",
address = "United States",

}

TY - GEN

T1 - Long-short term memory neural network stability and stabilization using linear matrix inequalities

AU - Deka, Shankar A.

AU - Stipanovic, Dusan M

AU - Murmann, Boris

AU - Tomlin, Claire J.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - A global asymptotic stability condition for Long Short-Term Memory neural networks is presented in this paper. A linear matrix inequality optimization problem is used to describe this global stability condition. The linear matrix inequality formulation can be viewed as a way for stabilization of Long Short-Term Memory neural networks since the networks' weight matrices and biases can be essentially treated as control variables. The condition and how to compute numerical values for the weight matrices and biases are illustrated by some examples.

AB - A global asymptotic stability condition for Long Short-Term Memory neural networks is presented in this paper. A linear matrix inequality optimization problem is used to describe this global stability condition. The linear matrix inequality formulation can be viewed as a way for stabilization of Long Short-Term Memory neural networks since the networks' weight matrices and biases can be essentially treated as control variables. The condition and how to compute numerical values for the weight matrices and biases are illustrated by some examples.

UR - http://www.scopus.com/inward/record.url?scp=85066806192&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066806192&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2019.8702629

DO - 10.1109/ISCAS.2019.8702629

M3 - Conference contribution

AN - SCOPUS:85066806192

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

BT - 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -