Thiết kế bộ ước lượng trạng thái phụ thuộc độ trễ cho mạng nơ-ron hồi tiếp thời gian rời rạc với độ trễ biến đổi theo thời gian phân vùng rời rạc và phân tán vô hạn

Cognitive Neurodynamics - Tập 5 - Trang 133-143 - 2010
Chin-Wen Liao1, Chien-Yu Lu1
1Department of Industrial Education and Technology, National Changhua University of Education, Changhua, Taiwan, ROC

Tóm tắt

Bài báo này nghiên cứu vấn đề ước lượng trạng thái cho mạng nơ-ron hồi tiếp thời gian rời rạc với cả độ trễ biến đổi theo thời gian phân vùng rời rạc và phân tán vô hạn, trong đó độ trễ biến đổi theo thời gian phân vùng rời rạc nằm trong một khoảng nhất định. Các hàm kích hoạt được giả định là liên tục Lipschitz toàn cầu. Một điều kiện phụ thuộc độ trễ cho sự tồn tại của các bộ ước lượng trạng thái được đề xuất dựa trên các kỹ thuật giới hạn mới. Thông qua các giải pháp cho các bất đẳng thức ma trận tuyến tính nhất định, các bộ ước lượng trạng thái tổng quát của bậc đầy đủ được thiết kế đảm bảo tính ổn định bất biến toàn cầu. Tính năng nổi bật là không cần bất đẳng thức để tìm kiếm các giới hạn trên cho tích vô hướng giữa hai vector, điều này có thể giảm bớt sự bảo thủ của tiêu chí bằng cách sử dụng các kỹ thuật giới hạn mới. Hai ví dụ minh họa được đưa ra để chứng minh hiệu quả và khả năng áp dụng của phương pháp đề xuất.

Từ khóa

#mạng nơ-ron hồi tiếp #ước lượng trạng thái #độ trễ biến đổi theo thời gian #Lipschitz #bất đẳng thức ma trận tuyến tính

Tài liệu tham khảo

Arena P, Muscato G, Fortuna L (1998) Neural networks in multidimensional domains: fundamentals and new trends in modelling and control. Springer, Berlin Arik S (2003) Global asymptotic stability of a larger class of neural networks with constant time delay. Phys Lett A 311:504–511 Boukis C, Mandic DP, Constantinides AG, Polymenakos LC (2006) A novel algorithm for the adaptation of the pole of Laguerre filters 13:429–432 Boyd S, Ei Ghaoui L, Feron E, Balakrishnan V (1994) Linear matrix inequalities in system and control theory. SIAM, Philadelphia, PA Cao J, Wang J (2003) Global asymptotic stability of a general class of recurrent neural networks with time-varying delays. IEEE Trans Circuits Syst I Fundam Theory Appl 50:34–44 Cao J, Wang J (2005) Global asymptotic and robust stability of recurrent neural networks with time delays. IEEE Trans Circuits Syst I Regul Pap 52:417–426 Cao J, Yuan K, Li HX (2006) Global asymptotical stability of recurrent neural networks with multiple discrete delays and distributed delays. IEEE Trans Neural Netw 17:1646–1651 Cao J, Ho DWC, Huang X (2007) LMI-based criteria for global robust stability of bidirectional associative memory networks with time delay. Nonlinear Anal 66:1558–1572 Chen WH, Lu X, Liang DY (2006) Global exponential stability for discrete-time neural networks with variable delays. Phys Lett A 358:186–198 Elanayar VTS, Shin YC (1994) Approximation and estimation of nonlinear stochastic dynamic systems using radial basis function neural networks. IEEE Trans Neural Netw 5:594–603 Gahinet P, Nemirovsky A, Laub AJ, Chilali M (1995) LMI control toolbox: for use with matlab. The Math Works, Natick, MA He Y, Wang QG, Wu M, Lin C (2006) Delay-dependent state estimation for delayed neural networks. IEEE Trans Neural Netw 7:1077–1081 Hirose A (2006) Complex-valued neural networks: theories and applications. World Scientific Publishing, New Jersey Hu S, Wang J (2006) Global robust stability of a class of discrete-time interval neural networks. IEEE Trans Circuits Syst Part I Regul 53:129–138 Huang H, Feng G, Cao J (2008) Robust state estimation for uncertain neural networks with time-varying delay. IEEE Trans Neural Netw 19:1329–1339 Jiao X, Wang R (2007) Synchronous firing and its control in neuronal population with time delay. Adv Cogn Neurodyn 213–217 Jiao X, Wang R (2010) Synchronous firing patterns of neuronal population with excitatory and inhibitory connections. Int J Non-linear Mech 45:647–651 Kuang Y, Smith H, Martin R (1991) Global stability for infinite-delay, dispersive Lotka-Volterra systems: weakly interacting populations in nearly identical patches. J Dyn Differ Equ 3:339–360 Li T, Fei SM (2007) Exponential state estimation for recurrent neural networks with distributed delays. Neurocomputing 71:428–438 Liang J, Cao J (2005) Convergence of discrete-time recurrent neural networks with variable delay. Int J Bifurcat Chaos 15:595–5811 Liu P, Han QL (2007) Discrete-time analogs for a class of continuous-time recurrent neural networks. IEEE Trans Neural Netw 18:1343–1355 Liu Y, Wang Z, Liu X (2007) Design of exponential state estimators for neural networks with mixed time delays. Phys Lett A 364:401–412 Liu Y, Wang Z, Liu X (2009) Asymptotic stability for neural networks with mixed time-delays: the discrete-time case. Neural Netw 22:67–74 Lu CY (2007) A delay-range-dependent approach to global robust stability for discrete-time uncertain recurrent neural networks with interval time-varying delay. Proc IMechE Part I J Syst Control Eng 221:1123–1132 Lu CY (2008) A delay-range-dependent approach to design state estimator for discrete-time recurrent neural networks with interval time-varying delay. IEEE Trans Circuits Syst-II Express Briefs 55:1163–11767 Mandic DP, Chambers JA (2001) Recurrent neural networks for prediction: learning algorithms, architectures and stability. Wiley, New York Mandic PD, Goh V (2009) Complex valued nonlinear adaptive filters: noncircularity, widely linear and neural models. Wiley, New York Moon YS, Park P, Kwon WH, Lee YS (2001) Delay-dependent robust stabilization of uncertain state-delayed systems. Int J Control 74(14):1447–1455 Park JH (2006) On global stability criterion for neural networks with discrete and distributed delays. Chaos Solitons Fractals 30:897–902 Parlos AG, Menon SK, Atiya AF (2001) An algorithmic approach to adaptive state filtering using recurrent neural networks. IEEE Trans Neural Netw 12:1411–14321 Principle JC, Kuo JM, Celebi S (1994) An analysis of the gamma memory in dynamic neural networks. IEEE Trans Neural Netw 5:337–361 Qi H (2007) New sufficient conditions for global robust stability of delayed neural networks. IEEE Trans Circuits Syst I Regul Pap 54:1131–1141 Shen Y, Wang J (2008) An improved algebraic criterion for global exponential stability of recurrent neural networks with time-varying delays. IEEE Trans Neural Netw 19:528–531 Shi P, Zhang J, Qiu J, Xing L (2007) New global asymptotic stability criterion for neural networks with discrete and distributed delays. Proc IMECHE Part I J Syst Control Eng 221:129–135 Shu H, Wang Z, Liu Z (2009) Global asymptotic stability of uncertain stochastic bi-directional associative memory networks with discrete and distributed delays. Math Comput Simul 80:490–505 Tank DW, Hopfield JJ (1987) Neural computation by concentrating information in time. Proc Natl Acad Sci USA 84:1896–1991 Wang L, Xu Z (2006) Sufficient and necessary conditions for global exponential stability of discrete-time recurrent neural networks. IEEE Trans Circuits Syst-I Regul Pap 53:1373–1380 Wang Z, Liu Y, Liu X (2005) On global asymptotic stability of neural networks with discrete and distributed delays. Phys Lett A 345:299–308 Wei G, Feng G, Wang Z (2009) Robust H ∞ control for discrete-time fuzzy systems with infinite-distributed delays. IEEE Trans Fuzzy Syst 17:224–232 Xie L, Fridman E, Shaked U (2001) Robust H ∞ control of distributed delay systems with application to combustion control. IEEE Trans Automat Contr 46:1930–1935 Xu S, Lam J, Ho DWC, Zou Y (2005) Delay-dependent exponential stability for a class of neural networks with time delays. J Comput Appl Math 183:16–28 Yu GJ, Lu CY, Tsai JSH, Liu BD, Su TJ (2003) Stability of cellular neural networks with time-varying delay. IEEE Trans Circuits Syst-I Fundam Theory Appl 50:677–678