Stochastic and hybrid approaches toward robust templates

In this paper, we propose and compare different methods of synthesizing robust templates for cellular neural networks. In a first approach, genetic algorithms are used for both template learning and optimization with respect to robustness. The evaluation of the fitness functions in the optimization step is computationally very expensive; a massively parallel supercomputer is used to achieve acceptable run times. As alternatives, a steepest ascent method and an averaging approach are presented, the latter being computationally inexpensive. To overcome their respective drawbacks, these algorithms are finally combined into a hybrid approach which is shown to be efficient even for complex problems.