Global Inverse Design across Multiple Photonic Structure Classes Using Generative Deep Learning (Advanced Optical Materials 20/2021)

In article number 2100548, Christopher Yeung, Aaswath P. Raman, and co-workers propose a global photonics and materials design framework, based on generative adversarial networks, which simultaneously optimizes a photonic system's device class, material properties, and geometric structuring. This framework is demonstrated in the context of metasurface design, where unique combinations of materials and structures are generated that yield significantly more variation in achievable optical responses than conventional deep learning and optimization-based approaches.