2020/07/20 by Jiaqi Jiang, Jonathan A. Fan · 55 citations
Computer Science · Engineering · Materials Science · Physics and Astronomy · #Artificial neural network #Categorical variable #Deep learning #Generative Design #Global optimization #Metamaterials and Metasurfaces Applications #Multi-objective optimization #Neural Networks and Reservoir Computing #Optimization problem #Photonic and Optical Devices #Photonics #cs.LG #physics.app-ph
paper · pdf · doi:10.1515/nanoph-2020-0407
published in Nanophotonics 10(1), 361-369 (De Gruyter)
arxiv created 2020/07/20 · openalex created_date 2020/07/29 · openalex publication_date 2020/09/22 · arxiv updated 2020/11/12 · openalex updated_date 2026/08/05
Abstract We show that deep generative neural networks, based on global optimization networks (GLOnets), can be configured to perform the multiobjective and categorical global optimization of photonic devices. A residual network scheme enables GLOnets to evolve from a deep architecture, which is required to properly search the full design space early in the optimization process, to a shallow network that generates a narrow distribution of globally optimal devices. As a proof‐of‐concept demonstration, we adapt our method to design thin‐film stacks consisting of multiple material types. Benchmarks with known globally optimized antireflection structures indicate that GLOnets can find the global optimum with orders of magnitude faster speeds compared to conventional algorithms. We also demonstrate the utility of our method in complex design tasks with its application to incandescent light filters. These results indicate that advanced concepts in deep learning can push the capabilities of inverse design algorithms for photonics.