Chin. Phys. B ›› 2012, Vol. 21 ›› Issue (12): 120701-120701.doi: 10.1088/1674-1056/21/12/120701

• GENERAL • 上一篇    下一篇

Novel delay-distribution-dependent stability analysis for continuous-time recurrent neural networks with stochastic delay

王申全a, 冯健a, 赵青b   

  1. a College of Information Science and Engineering, Northeastern University, Shenyang 110819, China;
    b Department of Electrical and Computer Engineering, University of Alberta, Edmonton T6G2V4, Canada
  • 收稿日期:2012-05-11 修回日期:2012-06-14 出版日期:2012-11-01 发布日期:2012-11-01
  • 基金资助:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 61273164, 61034005, and 60974071), the National High Technology Research and Development Program of China (Grant No. 2012AA040104), and the Fundamental Research Funds for the Central Universities (Grant Nos. N100104102 and N110604007).

Novel delay-distribution-dependent stability analysis for continuous-time recurrent neural networks with stochastic delay

Wang Shen-Quan (王申全)a, Feng Jian (冯健)a, Zhao Qing (赵青)b   

  1. a College of Information Science and Engineering, Northeastern University, Shenyang 110819, China;
    b Department of Electrical and Computer Engineering, University of Alberta, Edmonton T6G2V4, Canada
  • Received:2012-05-11 Revised:2012-06-14 Online:2012-11-01 Published:2012-11-01
  • Contact: Feng Jian E-mail:fjneu@163.com
  • Supported by:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 61273164, 61034005, and 60974071), the National High Technology Research and Development Program of China (Grant No. 2012AA040104), and the Fundamental Research Funds for the Central Universities (Grant Nos. N100104102 and N110604007).

PDF (PC)

553

赞

摘要： In this paper, the problem of delay-distribution-dependent stability is investigated for continuous-time recurrent neural networks (CRNNs) with stochastic delay. Different from the common assumptions on time delays, it is assumed that the probability distribution of the delay taking values in some intervals is known a priori. By making full use of the information concerning the probability distribution of the delay and by using a tighter bounding technique (reciprocally convex combination method), less conservative asymptotic mean-square stable sufficient conditions are derived in terms of linear matrix inequalities (LMIs). Two numerical examples show that our results are better than the existing ones.

关键词: recurrent neural networks, stochastic delay, mean-square stability, linear matrix inequality

Abstract: In this paper, the problem of delay-distribution-dependent stability is investigated for continuous-time recurrent neural networks (CRNNs) with stochastic delay. Different from the common assumptions on time delays, it is assumed that the probability distribution of the delay taking values in some intervals is known a priori. By making full use of the information concerning the probability distribution of the delay and by using a tighter bounding technique (reciprocally convex combination method), less conservative asymptotic mean-square stable sufficient conditions are derived in terms of linear matrix inequalities (LMIs). Two numerical examples show that our results are better than the existing ones.

Key words: recurrent neural networks, stochastic delay, mean-square stability, linear matrix inequality

中图分类号:  (Neural networks, fuzzy logic, artificial intelligence)

  • 07.05.Mh
02.10.Yn (Matrix theory) 02.30.Yy (Control theory)