Convergence of a Class of Cooperative Standard Cellular Neural Network Arrays

This paper considers a nonsymmetric standard (S) cellular neural network (CNN) array with cooperative (nonnegative) interconnections between neurons and a typical three-segment piecewise-linear (PL) neuron activation. The CNN is defined by a one-dimensional cell-linking (irreducible) cloning template with nearest-neighbor interconnections and has periodic boundary conditions. The flow generated by the SCNN is monotone but, due to the squashing effect of the horizontal segments in the PL activations, is not eventually strongly monotone (ESM). A new method for addressing convergence of the cooperative SCNN array is developed, which is based on the two main tools: (1) the concept of a frozen saddle, i.e., an unstable saddle-type equilibrium point (EP) enjoying certain dynamical properties that hold also for an asymptotically stable EP (a sink); (2) the analysis of the order relations satisfied by the sinks and saddle-type EPs. The analysis permits to show a fundamental result according to which any pair of ordered EPs of the SCNN contains at least a sink or a frozen saddle. On this basis it is shown that the flow generated by the SCNN enjoys a LIMIT SET DICHOTOMY and convergence properties analogous to those valid for ESM flows. Such results hold in the case where the SCNN displays either a local diffusion or a global propagation behavior.

[1]  Leon O. Chua,et al.  Stability of a class of nonreciprocal cellular neural networks , 1990 .

[2]  Leon O. Chua,et al.  Pattern formation properties of autonomous Cellular Neural Networks , 1995 .

[3]  Morris W. Hirsch,et al.  Convergent activation dynamics in continuous time networks , 1989, Neural Networks.

[4]  Chih-Wen Shih,et al.  On the Templates Corresponding to Cycle-Symmetric Connectivity in Cellular Neural Networks , 2002, Int. J. Bifurc. Chaos.

[5]  Leon O. Chua,et al.  On the universe of stable cellular neural networks , 1992, Int. J. Circuit Theory Appl..

[6]  Jinde Cao,et al.  Global Synchronization in an Array of Delayed Neural Networks With Hybrid Coupling , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[7]  Huaguang Zhang,et al.  Improved Robust Stability Criteria for Delayed Cellular Neural Networks via the LMI Approach , 2010, IEEE Transactions on Circuits and Systems II: Express Briefs.

[8]  M. Grazzini,et al.  The dichotomy of omega-limit sets fails for cooperative standard CNNs , 2010, 2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010).

[9]  David Angeli,et al.  Attractors in coherent systems of differential equations , 2007, 0710.3507.

[10]  Horst R. Thieme,et al.  Quasi convergence and stability for strongly order-preserving semiflows , 1990 .

[11]  M V Makarets,et al.  SYSTEMS OF DIFFERENTIAL EQUATIONS , 1995 .

[12]  R. Bellman Introduction To Matrix Analysis Second Edition , 1997 .

[13]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[14]  Alberto Tesi,et al.  A New Method to Analyze Complete stability of PWL Cellular Neural Networks , 2001, Int. J. Bifurc. Chaos.

[15]  Hiroshi Matano,et al.  Existence of nontrivial unstable sets for equilibriums of strongly order-preserving systems , 1984 .

[16]  Patrick Thiran,et al.  An approach to information propagation in cellular neural networks - Part I : Local diffusion , 1998 .

[17]  Chih-Wen Shih Influence of Boundary Conditions on Pattern Formation and Spatial Chaos in Lattice Systems , 2000, SIAM J. Appl. Math..

[18]  A. Michel,et al.  Analysis and synthesis of a class of neural networks: linear systems operating on a closed hypercube , 1989 .

[19]  P. Thiran,et al.  An approach to information propagation in 1-D cellular neural networks. II. Global propagation , 1998 .

[20]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[21]  L. Chua Cnn: A Paradigm for Complexity , 1998 .

[22]  Joos Vandewalle,et al.  High speed calculation of cryptographic hash functions by CNN chips , 1998, 1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359).

[23]  M. Hirsch,et al.  4. Monotone Dynamical Systems , 2005 .

[24]  Jinde Cao,et al.  Global synchronization in arrays of delayed neural networks with constant and delayed coupling , 2006 .

[25]  Michael Peter Kennedy,et al.  Unifying the Tank and Hopfield linear programming circuit and the canonical nonlinear programming circuit of Chua and Lin , 1987 .

[26]  Leon O. Chua,et al.  Methods for image processing and pattern formation in Cellular Neural Networks: a tutorial , 1995 .

[27]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[28]  Hal L. Smith,et al.  Monotone Dynamical Systems: An Introduction To The Theory Of Competitive And Cooperative Systems (Mathematical Surveys And Monographs) By Hal L. Smith , 1995 .

[29]  R. May,et al.  Nonlinear Aspects of Competition Between Three Species , 1975 .

[30]  A. Tesi,et al.  New conditions for global stability of neural networks with application to linear and quadratic programming problems , 1995 .

[31]  Chung-Yu Wu,et al.  Stability Analysis of Autonomous Ratio-Memory Cellular Nonlinear Networks for Pattern Recognition , 2010, IEEE Transactions on Circuits and Systems I: Regular Papers.

[32]  Tianping Chen,et al.  New Conditions on Global Stability of Cohen-Grossberg Neural Networks , 2003, Neural Computation.

[33]  M. Hirsch Stability and convergence in strongly monotone dynamical systems. , 1988 .

[34]  Leon O. Chua,et al.  Design of linear cellular neural networks for motion sensitive filtering , 1993 .

[35]  Qiankun Song,et al.  Multistability in Networks With Self-Excitation and High-Order Synaptic Connectivity , 2010, IEEE Transactions on Circuits and Systems I: Regular Papers.

[36]  Mauro Forti,et al.  A note on the dichotomy of limit sets for cooperative CNNs with delays , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[37]  Alberto Tesi,et al.  The Lojasiewicz Exponent at an Equilibrium Point of a Standard CNN is 1/2 , 2006, Int. J. Bifurc. Chaos.

[38]  Jinde Cao,et al.  Global asymptotic and robust stability of recurrent neural networks with time delays , 2005, IEEE Trans. Circuits Syst. I Regul. Pap..

[39]  L. Chua,et al.  Synchronization in an array of linearly coupled dynamical systems , 1995 .

[40]  Chih-Wen Shih,et al.  Complete stability for a Class of Cellular Neural Networks , 2001, Int. J. Bifurc. Chaos.

[41]  G. Grassi,et al.  On discrete-time cellular neural networks for associative memories , 2001 .

[42]  Horst R. Thieme,et al.  Convergence for strongly order-preserving semiflows , 1991 .

[43]  Leon O. Chua,et al.  Cellular neural networks: applications , 1988 .

[44]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[45]  Patrick Thiran,et al.  Dynamics and self-organization of locally coupled neural networks , 1996 .

[46]  Lihong Huang,et al.  Dynamics of smooth essentially strongly order-preserving semiflows with application to delay differential equations , 2008 .

[47]  Jifa Jiang,et al.  On the ω-limit Set Dichotomy of Cooperating Kolmogorov Systems , 2003 .

[48]  Shen-Ping Xiao,et al.  New Globally Asymptotic Stability Criteria for Delayed Cellular Neural Networks , 2009, IEEE Transactions on Circuits and Systems II: Express Briefs.

[49]  Lihong Huang,et al.  Convergence and stability for essentially strongly order-preserving semiflows , 2006 .

[50]  Hal L. Smith,et al.  Strongly order preserving semiflows generated by functional differential equations , 1991 .

[51]  Mauro Forti,et al.  Limit Set Dichotomy and Convergence of semiflows Defined by Cooperative Standard CNNs , 2010, Int. J. Bifurc. Chaos.

[52]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[53]  M. Hirsch Systems of Differential Equations that are Competitive or Cooperative II: Convergence Almost Everywhere , 1985 .

[54]  Mauro Forti,et al.  Limit Set Dichotomy and Convergence of Cooperative Piecewise Linear Neural Networks , 2011, IEEE Transactions on Circuits and Systems I: Regular Papers.

[55]  Leon O. Chua,et al.  Stability and dynamics of delay-type general and cellular neural networks , 1992 .

[56]  E. Kaszkurewicz,et al.  On a class of globally stable neural circuits , 1994 .

[58]  Richard Bellman,et al.  Introduction to matrix analysis (2nd ed.) , 1997 .