Design and training of multilayer discrete time cellular neural networks for antipersonnel mine detection using genetic algorithms
Paula Lopez, Marco Balsi, D.L. Vilariño, D. Cabello · 2002
In this work we present a novel strategy for the simultaneous design and training of multilayer discrete-time cellular neural networks. This methodology is applied to the detection of surface-laid antipersonnel mines in infrared imaging. The procedure is based on the application of genetic algorithms for both network design and learning task.