Genetic optimization of cellular neural networks

The operation of a cellular neural network (CNN) is defined by a set of 19 parameters. There is no known general method for finding these parameters; analytic design methods are available for a small class of problems only. Standard learning algorithms cannot be applied due to the lack of gradient information. The authors propose a genetic algorithm as a generally applicable global learning method. In order to be useful for real CNN VLSI chips, the parameters have to be insensitive to small perturbations Therefore, after the parameters are learnt they are optimized with respect to robustness in a second genetic processing step. As the simulation of CNNs necessitates the numerical integration of large systems of nonlinear differential equations, the evaluation of the fitness functions is computationally very expensive; a massively parallel supercomputer is used to achieve acceptable run times.

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

[2]  Leon O. Chua,et al.  Genetic algorithm for CNN template learning , 1993 .

[3]  B. Mirzai,et al.  Robust CNN templates: theory and simulations , 1996, 1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96).

[4]  Kari Halonen,et al.  Robust CMOS CNN implementation with respect to manufacturing inaccuracies , 1996, 1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96).

[5]  Ángel Rodríguez-Vázquez,et al.  Realization of a CNN universal chip in CMOS technology , 1995, Proceedings of ISCAS'95 - International Symposium on Circuits and Systems.

[6]  George S. Moschytz,et al.  Visualisation of CNN dynamics , 1997 .

[7]  D. Lim,et al.  A programmable, modular CNN cell , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

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

[9]  George S. Moschytz,et al.  Upper bounds for robustness of CNN templates and a design approach for robust templates , 1996, 1996 IEEE International Symposium on Circuits and Systems. Circuits and Systems Connecting the World. ISCAS 96.