Improved sufficient convergence condition for the discrete-time cellular neural networks

In this paper, we derive an improved sufficient convergence condition for discrete-time cellular neural networks (DTCNN) using the positive semidefinite (PSD) constraint and the boundary condition of DTCNN. The experimental results confirm that the derived condition offers a wider convergence range than the convergence condition of Fruehauf (1992). The new condition does not depend on the type of the nonlinear output function of the DTCNN.

[1]  R. Perfetti.  Relation between template spectrum and convergence of discrete-time cellular neural networks , 1993 .

[2]  Hubert Harrer.  Discrete time cellular neural networks , 1992, Int. J. Circuit Theory Appl..

[3]  N. Fruehauf,et al.  Convergence of reciprocal time-discrete cellular neural networks with continuous nonlinearities , 1992, CNNA '92 Proceedings Second International Workshop on Cellular Neural Networks and Their Applications.

[4]  D. Kelly,et al.  Stability in contractive nonlinear neural networks , 1990, IEEE Transactions on Biomedical Engineering.

[5]  Robert M. Gray,et al.  On the asymptotic eigenvalue distribution of Toeplitz matrices , 1972, IEEE Trans. Inf. Theory.

[6]  Stefen Hui,et al.  Dynamical analysis of the brain-state-in-a-box (BSB) neural models , 1992, IEEE Trans. Neural Networks.