Long-Short Term Memory Neural Network Stability and Stabilization using Linear Matrix Inequalities

Shankar A. Deka, Dušan M. Stipanović, Boris Murmann, Claire J. Tomlin

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

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
Title of host publication2019 IEEE International Symposium on Circuits and Systems (ISCAS)
PublisherIEEE
Pages1-4
Number of pages4
ISBN (Print)978-1-7281-0397-6
DOIs
Publication statusPublished - 29 May 2019
MoE publication typeA4 Conference publication
EventIEEE International Symposium on Circuits and Systems - Sapporo, Japan, Sapporo, Japan
Duration: 26 May 201929 May 2019

Conference

ConferenceIEEE International Symposium on Circuits and Systems
Abbreviated titleISCAS
Country/TerritoryJapan
CitySapporo
Period26/05/201929/05/2019

Keywords

  • Asymptotic stability
  • Numerical stability
  • Stability analysis
  • Mathematical model
  • Linear matrix inequalities
  • Neural networks
  • Chaos

Fingerprint

Dive into the research topics of 'Long-Short Term Memory Neural Network Stability and Stabilization using Linear Matrix Inequalities'. Together they form a unique fingerprint.

Cite this