Implementation of cellular genetic algorithms on a CNN chip: Simulations and experimental results
András Horváth, Miklós Rásonyi · International Journal of Circuit Theory and Applications · 2012
SUMMARY One of the most challenging recent problems in engineering is the development of proper topographic and parallel algorithms that can exploit the high performance of multi‐parallel architectures like cellular neural networks. We have developed, simulated and implemented a cellular version of the well‐known genetic algorithm which ideally suits these devices. The paper contains not only simulations, but an actual implementation and performance analysis on an existing architecture, theXenon _ v3 digital cellular network, its emulator and its compiler. We support our conclusions by testing the algorithm on the traveling salesman problem. Copyright © 2012 John Wiley & Sons, Ltd.