Łojasiewicz inequality and exponential convergence of the full-range model of CNNs

This paper considers the Full-range (FR) model of Cellular Neural Networks (CNNs) in the case where the signal range is delimited by an ideal hard-limiter nonlinearity with two vertical segments in the i−v characteristic. A Łojasiewicz inequality around any equilibrium point, for a FRCNN with a symmetric interconnection matrix, is proved. It is also shown that the Łojasiewicz exponent is equal to **image**. The main consequence is that any forward solution of a symmetric FRCNN has finite length and is exponentially convergent toward an equilibrium point, even in degenerate situations where the FRCNN possesses non-isolated equilibrium points. The obtained results are shown to improve the previous results in literature on convergence or almost convergence of symmetric FRCNNs. Copyright © 2010 John Wiley & Sons, Ltd.

[1]  Mauro Forti,et al.  On global exponential stability of standard and full-range CNNs , 2008 .

[2]  Fernando Corinto,et al.  Comparison between the dynamic behaviour of Chua–Yang and full‐range cellular neural networks , 2003, Int. J. Circuit Theory Appl..

[3]  Mauro Forti,et al.  Convergence of Neural Networks for Programming Problems via a Nonsmooth Łojasiewicz Inequality , 2006, IEEE Transactions on Neural Networks.

[4]  Wei Bian,et al.  Subgradient-Based Neural Networks for Nonsmooth Nonconvex Optimization Problems , 2009, IEEE Transactions on Neural Networks.

[5]  Ángel Rodríguez-Vázquez,et al.  ACE16k: the third generation of mixed-signal SIMD-CNN ACE chips toward VSoCs , 2004, IEEE Transactions on Circuits and Systems I: Regular Papers.

[6]  Pierre-Antoine Absil,et al.  Continuous dynamical systems that realize discrete optimization on the hypercube , 2004, Syst. Control. Lett..

[7]  Mauro Forti,et al.  Lyapunov Method and Convergence of the Full-Range Model of CNNs , 2008, IEEE Transactions on Circuits and Systems I: Regular Papers.

[8]  Mauro Forti,et al.  Dynamical Analysis of Full-Range Cellular Neural Networks by Exploiting Differential Variational Inequalities , 2007, IEEE Transactions on Circuits and Systems I: Regular Papers.

[9]  Ángel Rodríguez-Vázquez,et al.  ACE16k: A 128x128 Focal Plane Analog Processor with Digital I/O , 2003, Int. J. Neural Syst..

[10]  Ángel Rodríguez-Vázquez,et al.  ACE4k: An analog I/O 64×64 visual microprocessor chip with 7-bit analog accuracy , 2002, Int. J. Circuit Theory Appl..

[11]  Adrian S. Lewis,et al.  The [barred L]ojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems , 2006, SIAM J. Optim..

[12]  Werner Römisch,et al.  Lipschitz Stability for Stochastic Programs with Complete Recourse , 1996, SIAM J. Optim..

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

[14]  Á. Rodríguez-Vázquez,et al.  Current-mode techniques for the implementation of continuous- and discrete-time cellular neural networks , 1993 .

[15]  Ángel Rodríguez-Vázquez,et al.  A VLSI-oriented continuous-time CNN model , 1996 .

[16]  Alberto Tesi,et al.  Absolute stability of analytic neural networks: an approach based on finite trajectory length , 2004, IEEE Transactions on Circuits and Systems I: Regular Papers.

[17]  Mauro Forti,et al.  Extended LaSalle's Invariance Principle for Full-Range Cellular Neural Networks , 2008, 2008 11th International Workshop on Cellular Neural Networks and Their Applications.

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

[19]  Ángel Rodríguez-Vázquez,et al.  ACE4k: An analog I/O 64×64 visual microprocessor chip with 7-bit analog accuracy: Research Articles , 2002 .

[20]  Jun Wang,et al.  Convergence Analysis of a Class of Nonsmooth Gradient Systems , 2008, IEEE Transactions on Circuits and Systems I: Regular Papers.

[21]  Robert E. Mahony,et al.  Convergence of the Iterates of Descent Methods for Analytic Cost Functions , 2005, SIAM J. Optim..

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