A hybrid optimization technique is used to synthesize frequency selective surface (FSS) structures composed of periodic arrays of integrated rings and dipole patch elements, printed on dielectric substrates, for microwave filtering applications. The optimization technique is based on the combination of genetic algorithms and neural networks. This hybrid optimization technique is used to determine specific values for the resonant frequency and bandwidth from variations of the FSS structural parameters, such as patch element and periodic array dimensions. The synthesized FSS structure is also analyzed using a fast and accurate wave concept iterative procedure for comparison purpose. Thereafter, prototypes are built and measured. A good agreement is observed between simulated and measured results. © 2014 Wiley Periodicals, Inc. Microwave Opt Technol Lett 56:329–333, 2014