A Degree-Dependent Polynomial-Based Reciprocally Convex Matrix Inequality and Its Application to Stability Analysis of Delayed Neural Networks
In this article, several improved stability criteria for time-varying delayed neural networks (DNNs) are proposed. A degree-dependent polynomial-based reciprocally convex matrix inequality (RCMI) is proposed for obtaining less conservative stability criteria. Unlike previous RCMIs, the matrix inequality in this article produces a polynomial of any degree in the time-varying delay, which helps to reduce conservatism. In addition, to reduce the computational complexity caused by dealing with the negative definite of the high-degree terms, an improved lemma is presented. Applying the above matrix inequalities and improved negative definiteness condition helps to generate a more relaxed stability criterion for analyzing time-varying DNNs. Two examples are provided to illustrate this statement.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:PP |
|---|---|
| Enthalten in: |
IEEE transactions on cybernetics - PP(2024) vom: 28. Feb. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Wang, Chen-Rui [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Revised 28.02.2024 published: Print-Electronic Citation Status Publisher |
|---|
| doi: |
10.1109/TCYB.2024.3365709 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM369065549 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM369065549 | ||
| 003 | DE-627 | ||
| 005 | 20240229235541.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240229s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TCYB.2024.3365709 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1311.xml |
| 035 | |a (DE-627)NLM369065549 | ||
| 035 | |a (NLM)38416629 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Wang, Chen-Rui |e verfasserin |4 aut | |
| 245 | 1 | 2 | |a A Degree-Dependent Polynomial-Based Reciprocally Convex Matrix Inequality and Its Application to Stability Analysis of Delayed Neural Networks |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 28.02.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status Publisher | ||
| 520 | |a In this article, several improved stability criteria for time-varying delayed neural networks (DNNs) are proposed. A degree-dependent polynomial-based reciprocally convex matrix inequality (RCMI) is proposed for obtaining less conservative stability criteria. Unlike previous RCMIs, the matrix inequality in this article produces a polynomial of any degree in the time-varying delay, which helps to reduce conservatism. In addition, to reduce the computational complexity caused by dealing with the negative definite of the high-degree terms, an improved lemma is presented. Applying the above matrix inequalities and improved negative definiteness condition helps to generate a more relaxed stability criterion for analyzing time-varying DNNs. Two examples are provided to illustrate this statement | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Long, Fei |e verfasserin |4 aut | |
| 700 | 1 | |a Xie, Ke-You |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Hui-Ting |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Chuan-Ke |e verfasserin |4 aut | |
| 700 | 1 | |a He, Yong |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE transactions on cybernetics |d 2013 |g PP(2024) vom: 28. Feb. |w (DE-627)NLM218340567 |x 2168-2275 |7 nnns |
| 773 | 1 | 8 | |g volume:PP |g year:2024 |g day:28 |g month:02 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/TCYB.2024.3365709 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d PP |j 2024 |b 28 |c 02 | ||