Please wait a minute...
Frontiers of Electrical and Electronic Engineering

ISSN 2095-2732

ISSN 2095-2740(Online)

CN 10-1028/TM

Front Elect Electr Eng    2012, Vol. 7 Issue (1) : 32-48    https://doi.org/10.1007/s11460-012-0186-y
REVIEW ARTICLE
Dynamical behaviors of recurrently connected neural networks and linearly coupled networks with discontinuous right-hand sides
Wenlian LU(), Tianping CHEN, Bo LIU, Xiangnan HE
School of Mathematical Sciences, Fudan University, Shanghai 200433, China
 Download: PDF(400 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

The aim of this paper is to provide a systematic review on the framework to analyze dynamics in recurrently connected neural networks with discontinuous right-hand sides with a focus on the authors’ works in the past three years. The concept of the Filippov solution is employed to define the solution of the neural network systems by transforming them to differential inclusions. The theory of viability provides a tool to study the existence and uniqueness of the solution and the Lyapunov function (functional) approach is used to investigate the global stability and synchronization. More precisely, we prove that the diagonal-dominant conditions guarantee the existence, uniqueness, and stability of a general class of integro-differential equations with (almost) periodic self-inhibitions, interconnection weights, inputs, and delays. This model is rather general and includes the well-known Hopfield neural networks, Cohen-Grossberg neural networks, and cellular neural networks as special cases. We extend the absolute stability analysis of gradient-like neural network model by relaxing the analytic constraints so that they can be employed to solve optimization problem with non-smooth cost functions. Furthermore, we study the global synchronization problem of a class of linearly coupled neural network with discontinuous right-hand sides.

Keywords delayed integro-differential system      discontinuous activation      almost periodic function      nonsmooth cost function      complete synchronization     
Corresponding Author(s): LU Wenlian,Email:wenlian@fudan.edu.cn   
Issue Date: 05 March 2012
 Cite this article:   
Wenlian LU,Tianping CHEN,Bo LIU, et al. Dynamical behaviors of recurrently connected neural networks and linearly coupled networks with discontinuous right-hand sides[J]. Front Elect Electr Eng, 2012, 7(1): 32-48.
 URL:  
https://academic.hep.com.cn/fee/EN/10.1007/s11460-012-0186-y
https://academic.hep.com.cn/fee/EN/Y2012/V7/I1/32
1 Cohen M A, Grossberg S. Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Transactions on Systems, Man, and Cybernetics , 1983, 13(5): 815-826
2 Hopfield J J. Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences of the United States of America , 1982, 79(8): 2554-2558
doi: 10.1073/pnas.79.8.2554
3 Hopfield J J. Neurons with graded response have collective computational properties like those of two-stage neurons. Proceedings of the National Academy of Sciences of the United States of America , 1984, 81(10): 3088-3092
doi: 10.1073/pnas.81.10.3088
4 Chua L O, Yang L. Cellular neural networks: Theory. IEEE Transactions on Circuits and Systems , 1988, 35(10): 1257-1272
doi: 10.1109/31.7600
5 Chua L O, Yang L. Cellular neural networks: Applications. IEEE Transactions on Circuits and Systems , 1988, 35(10): 1273-1290
doi: 10.1109/31.7601
6 Forti M, Tesi A. Absolute stability of analytic neural networks: An approach based on finite trajectory length. IEEE Transactions on Circuits and Systems I: Regular Papers , 2004, 51(12): 2460-2469
doi: 10.1109/TCSI.2004.838143
7 Civalleri P P, Gilli L M, Pandolfi L. On stability of cellular neural networks with delay. IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications , 1993, 40(3): 157-165
doi: 10.1109/81.222796
8 Chen T P, Lu W L, Chen G R. Dynamical behaviors of a large class of general delayed neural networks. Neural Computation , 2005, 17(4): 949-968
doi: 10.1162/0899766053429417
9 Lu W L, Chen T P. Global convergent dynamics of delayed neural networks. In: Atay F M, ed. Complex Time-Delay Systems, Understanding Complex Systems, Chapter 7. Springer-Verlag , 2010
10 Forti M, Nistri P. Global convergence of neural networks with discontinuous neuron activations. IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications , 2003, 50(11): 1421-1435
doi: 10.1109/TCSI.2003.818614
11 Harrer H, Nossek J A, Stelzl R. An analog implementation of discrete-time cellular neural networks. IEEE Transactions on Neural Networks , 1992, 3(3): 466-476
doi: 10.1109/72.129419
12 Kennedy M P, Chua L O. Neural networks for nonlinear programming. IEEE Transactions on Circuits and Systems , 1988, 35(5): 554-562
doi: 10.1109/31.1783
13 Utkin V I. Variable structure systems with sliding modes. IEEE Transactions on Automatic Control , 1977, 22(2): 212-222
doi: 10.1109/TAC.1977.1101446
14 Lojasiewicz S. Une propriet′e topologique des sous-ensembles analytiques r′eels, Colloques internationaux du C.N.R.S. Les ′Equations aux D′erive′es Partielles , 1963, 117: 87-89
15 Lojasiewicz S. Sur la g′eom′etrie semi- et sous-analytique. Annales de L’Institut Fourier , 1993, 43(5): 1575-1595
doi: 10.5802/aif.1384
16 Lu W L, Chen T P. Almost periodic dynamics of a class of delayed neural networks with discontinuous activations. Neural Computation , 2008, 20(4): 1065-1090
doi: 10.1162/neco.2008.10-06-364
17 Lu W L, Wang J. Convergence analysis of a class of nonsmooth gradient systems. IEEE Transactions on Circuits and Systems I: Regular Papers , 2008, 55(11): 3514-3527
doi: 10.1109/TCSI.2008.925816
18 He X N, Lu W L, Chen T P. Nonnegative periodic dynamics of delayed Cohen-Grossberg neural networks with discontinuous activations. Neurocomputing , 2010, 73(13-15): 2765-2772
doi: 10.1016/j.neucom.2010.04.006
19 Liu B, Lu WL, Chen T P. New conditions on synchronization of networks of linearly coupled dynamical systems with non-Lipschitz right-hand sides. Neural Networks , 2012, 25(1): 5-13
doi: 10.1016/j.neunet.2011.07.007
20 Filippov A F. Classical solution of differential equations with multivalued right-hand side. SIAM Journal on Control , 1967, 5(4): 609-621
doi: 10.1137/0305040
21 Aubin J P, Cellina A. Differential Inclusions . Berlin: Springer-Verlag, 1984
doi: 10.1007/978-3-642-69512-4
22 Aubin J P, Frankowska H. Set-Valued Analysis. Boston: Birkhauser, 1990
23 Aubin J P. Viability Theory. Boston: Birhauser, 1991
24 Haddad G. Monotine viable trajectories for functional differential inclusions. Journal of Differential Equations , 1981, 42(1): 1-24
doi: 10.1016/0022-0396(81)90031-0
25 Hale J. Theory of Functional Differential Equations. New York: Springer-Verlag, 1977
doi: 10.1007/978-1-4612-9892-2
26 Chen T P, Rong L B. Robust global exponential stability of Cohen-Grossberg neural networks with time delays. IEEE Transactions on Neural Networks , 2004, 15(1): 203-206
doi: 10.1109/TNN.2003.822974
27 Lu W L, Chen T P. New conditions on global stability of Cohen-Grossberg neural networks. Neural Computation , 2003, 15(5): 1173-1189
doi: 10.1162/089976603765202703
28 Lu WL, Chen T P. Dynamical behaviors of Cohen-Grossberg neural networks with discontinuous activation functions. Neural Networks , 2005, 18(3): 231-242
doi: 10.1016/j.neunet.2004.09.004
29 Grossberg S. Biological competition: Decision rules, pattern formation, and oscillations. Proceedings of the National Academy of Sciences of the United States of America , 1980, 77(4): 2338-2342
doi: 10.1073/pnas.77.4.2338
30 Grossberg S. Nonlinear neural networks: Principles, mechanisms, and architectures. Neural Networks , 1988, 1(1): 17-61
doi: 10.1016/0893-6080(88)90021-4
31 Forti M, Tesi A. The _Lojasiewicz exponent at equilibrium point of a standard CNN is 1/2. International Journal of Bifurcation and Chaos in Applied Sciences and Engineering , 2006, 16(8): 2191-2205
doi: 10.1142/S0218127406016008
32 Bolte J, Daniilidis A, Lewis A. The _Lojasiewicz inequality for nonsmooth functions with applications to subgradient dynamical systems. SIAM Journal on Optimization , 2007, 17(4): 1205-1223
doi: 10.1137/050644641
33 Krantz S G, Parks H R. A Primer of Real Analytic Functions. 2nd ed. Boston: Birkh?user, 2002
doi: 10.1007/978-0-8176-8134-0
34 Vidyasagar M. Minimum-seeking properties of analog neural networks with multilinear objective functions. IEEE Transactions on Automatic Control , 1995, 40(8): 1359-1375
doi: 10.1109/9.402228
35 Wu C W, Chua L O. Synchronization in an array of linearly coupled dynamical systems. IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications , 1995, 42(8): 430-447
doi: 10.1109/81.404047
36 Forti M, Nistri P, Papini D. Global exponential stability and global convergence in finite time of delayed neural networks with infinite gain. IEEE Transactions on Neural Networks , 2005, 16(6): 1449-1463
doi: 10.1109/TNN.2005.852862
37 Lu W L, Chen T P. Dynamical behaviors of delayed neural network systems with discontinuous activation functions. Neural Computation , 2006, 18(3): 683-708
doi: 10.1162/neco.2006.18.3.683
38 Papini D, Taddei V. Global exponential stability of the periodic solution of the delayed neural networks with discontinuous activations. Physics Letters A , 2005, 343(1-3): 117-128
doi: 10.1016/j.physleta.2005.06.015
39 Wang Y, Zuo Y, Huang L, Li C. Global robust stability of delayed neural networks with discontinuous activation functions. IET Control Theory & Applications , 2008, 2(7): 543-553
40 Liu X, Cao J. On periodic solutions of neural networks via differential inclusions. Neural Networks , 2009, 22(4): 329-334
doi: 10.1016/j.neunet.2008.11.003
41 Wang L. Multistability of almost periodic solutions of neural networks with discontinuous activation functions. In: Proceedings of the Third International Workshop on Advanced Computational Intelligence . 2010, 16-20
doi: 10.1109/IWACI.2010.5585222
42 Lin W, Chen T P. Positive periodic solutions of delayed periodic Lotka-Volterra systems. Physics Letters A , 2005, 334(4): 273-287
doi: 10.1016/j.physleta.2004.10.083
43 Lu WL, Chen T P. R+nRn+-global stability of a Cohen-Grossberg neural network system with nonnegative equilibria. Neural Networks , 2007, 20(6): 714-722
doi: 10.1016/j.neunet.2007.05.004
44 Forti M, Nistri P, Quincampoix M. Convergence of neural networks for programming problems via a nonsmooth Lojasiewicz inequality. IEEE Transactions on Neural Networks , 2006, 17(6): 1471-1486
doi: 10.1109/TNN.2006.879775
45 Bolte J, Daniilidis A, Lewis A. A nonsmooth Morse-Sard theorem for subanalytic functions. Journal of Mathematical Analysis and Applications , 2006, 321(2): 729-740
doi: 10.1016/j.jmaa.2005.07.068
46 Liu Q, Wang J. A one-layer recurrent neural network with a discontinuous hard-limiting activation function for quadratic programming. IEEE Transactions on Neural Networks , 2008, 19(4): 558-570
doi: 10.1109/TNN.2007.910736
47 Liu Q, Wang J. A one-layer recurrent neural network with a discontinuous activation function for linear programming. Neural Computation , 2008, 20(5): 1366-1383
doi: 10.1162/neco.2007.03-07-488
48 Belykh I, Belykh V, Hasler M. Blinking model and synchronization in small-world networks with a time-varying coupling. Physica D: Nonlinear Phenomena , 2004, 195(1-2): 188-206
doi: 10.1016/j.physd.2004.03.013
49 Pavlov A, Pogromsky A, van de Wouw N, Nijmeijer H. On convergence properties of piecewise affine systems. International Journal of Control , 2007, 80(8): 1233-1247
doi: 10.1080/00207170701261978
50 van de Wouw N, Pavlov A. Tracking and synchronisation for a class of PWA systems. Automatica , 2008, 44(11): 2909-2915
doi: 10.1016/j.automatica.2008.04.015
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed