Metamaterials are engineered composites that can achieved electromagnetic and mechanical properties that do not exist in natural materials by rearranging their structures. Due to the complexity of the objective functions, it is difficult to find the globally optimized solutions in metameterial design. This talk outlines a gradient-based optimization with generative networks that can search for the globally optimized cloaking devices over a wide range of parameters. The GLO-Net model was developed originally for one-dimensional nano-photonic metagratings is generalized in this work to design two-dimensional broadband acoustic cloaking devices by perturbing positions of each scatterer in planar configuration of cylindrical scatterers. Such optimized cloaking devices can efficiently suppress the total scattering cross section to the minimum at certain parameters over range of wavenumbers. During training each iteration, a generative model generates a batch of metamaterials and compute the total scattering cross section and its gradients using an in-house built multiple scattering MATLAB solver. To evaluate our approach, we compare our obtained results with fmincon in MATLAB.
 Jiaqi Jiang and Jonathan A. Fan. Simulator-based training of generative neural networks for the inverse design of metasurfaces. Nanophotonics, 9(5):10591069, nov 2019.