论文信息 - Lyapunov diagonally stable matrices to design cellular neural networks for associative memories

Lyapunov diagonally stable matrices to design cellular neural networks for associative memories

Lyapunov diagonally stable matrices are used to design cellular neural networks for associative memories. The proposed technique, which guarantees the global asymptotic stability of the equilibrium point, generates neural circuits where the input data are fed via external inputs, rather than initial conditions. This feature makes the suggested approach particularly suitable for hardware implementation techniques. Simulations results are reported to show the advantages and the usefulness of the proposed design method.

G. Grassi

[1] Leon O. Chua,et al. The CNN paradigm , 1993 .

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

[3] Derong Liu,et al. Sparsely interconnected neural networks for associative memories with applications to cellular neural networks , 1994 .

[4] M. Brucoli,et al. Associative memory design using discrete-time second-order neural networks with local interconnections , 1997 .

[5] G. Grassi,et al. A new approach to design cellular neural networks for associative memories , 1997 .

[6] Tamás Roska,et al. The CNN universal machine: an analogic array computer , 1993 .

[7] S. Espejo,et al. A CNN universal chip in CMOS technology , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[8] Ángel Rodríguez-Vázquez,et al. A CNN UNIVERSAL CHIP IN CMOS TECHNOLOGY , 1996 .

[9] M. Brucoli,et al. Implementation of cellular neural networks for heteroassociative and autoassociative memories , 1996, 1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96).

[10] M. Brucoli,et al. Discrete-time cellular neural networks for associative memories with learning and forgetting capabilities , 1995 .

[11] M. Brucoli,et al. A global approach to the design of discrete-time cellular neural networks for associative memories , 1996 .