中国物理B ›› 2011, Vol. 20 ›› Issue (5): 50505-050505.doi: 10.1088/1674-1056/20/5/050505

• • 上一篇    下一篇

New results on stability criteria for neural networks with time-varying delays

J.W. Kwon1, O.M. Kwon2, S.H. Kim3   

  1. (1)Department of Computer Engineering, Kyungwon University, San 65, Sujung-gu, Sungnam 461-701, Republic of Korea; (2)School of Electrical Engineering, Chungbuk National University, 410 SungBong-Ro, Heungduk-gu, Cheongju 361-763, Republic of Korea; (3)School of Integrated Technology, College of Engineering, Yonsei University, 50 Yonsei-Ro, Seodaemun-gu, Seoul 120-749, Republic of Korea
  • 收稿日期:2010-09-03 修回日期:2010-12-10 出版日期:2011-05-15 发布日期:2011-05-15
  • 基金资助:
    Project supported by the MKE (The Ministry of Knowledge Economy), Korea, under the ITRC (Information Technology Research Center) support program supervised by the IITA (Institute for Information Technology Advancement) (Grant No. IITA-2009-C1090-0904-0007

New results on stability criteria for neural networks with time-varying delays

O.M. Kwona)†, J.W. Kwonb), and S.H. Kimc)   

  1. a School of Electrical Engineering, Chungbuk National University, 410 SungBong-Ro, Heungduk-gu, Cheongju 361-763, Republic of Korea; b Department of Computer Engineering, Kyungwon University, San 65, Sujung-gu, Sungnam 461-701, Republic of Korea; c School of Integrated Technology, College of Engineering, Yonsei University, 50 Yonsei-Ro, Seodaemun-gu, Seoul 120-749, Republic of Korea
  • Received:2010-09-03 Revised:2010-12-10 Online:2011-05-15 Published:2011-05-15
  • Supported by:
    Project supported by the MKE (The Ministry of Knowledge Economy), Korea, under the ITRC (Information Technology Research Center) support program supervised by the IITA (Institute for Information Technology Advancement) (Grant No. IITA-2009-C1090-0904-0007).

PDF (PC)

883

赞

摘要： In this paper, the problem of stability analysis for neural networks with time-varying delays is considered. By constructing a new augmented Lyapunov–Krasovskii's functional and some novel analysis techniques, improved delay-dependent criteria for checking the stability of the neural networks are established. The proposed criteria are presented in terms of linear matrix inequalities (LMIs) which can be easily solved and checked by various convex optimization algorithms. Two numerical examples are included to show the superiority of our results.

关键词: neural networks, time-varying delays, stability, Lyapunov method

Abstract: In this paper, the problem of stability analysis for neural networks with time-varying delays is considered. By constructing a new augmented Lyapunov–Krasovskii's functional and some novel analysis techniques, improved delay-dependent criteria for checking the stability of the neural networks are established. The proposed criteria are presented in terms of linear matrix inequalities (LMIs) which can be easily solved and checked by various convex optimization algorithms. Two numerical examples are included to show the superiority of our results.

Key words: neural networks, time-varying delays, stability, Lyapunov method

中图分类号:  (Nonlinear dynamics and chaos)

  • 05.45.-a