Benchmarking deep learning-based models on nanophotonic inverse design problems
对基于深度学习的纳米光子逆设计问题模型进行基准测试
ナノフォトニック逆設計問題に関する深層学習ベースのモデルのベンチマーク
나노광자 역설계 문제에 대한 딥 러닝 기반 모델 벤치마킹
Evaluación comparativa de modelos basados en aprendizaje profundo en problemas de diseño inverso nanofotónico
Analyse comparative de modèles basés sur l'apprentissage profond sur des problèmes de conception inverse nanophotonique
Сравнительный анализ моделей, основанных на глубоком обучении, на обратных задачах проектирования нанофотоники
Taigao Ma ¹, Mustafa Tobah ², Haozhu Wang 王浩竹 ³, L. Jay Guo 郭凌杰 ³
¹ Department of Physics, The University of Michigan, Ann Arbor, Michigan, 48109, USA
² Department of Materials Science and Engineering, The University of Michigan, Ann Arbor, Michigan, 48109, USA
³ Department of Electrical Engineering and Computer Science, The University of Michigan, Ann Arbor, Michigan, 48109, USA
Photonic inverse design concerns the problem of finding photonic structures with target optical properties. However, traditional methods based on optimization algorithms are time-consuming and computationally expensive. Recently, deep learning-based approaches have been developed to tackle the problem of inverse design efficiently.
Although most of these neural network models have demonstrated high accuracy in different inverse design problems, no previous study has examined the potential effects under given constraints in nanomanufacturing. Additionally, the relative strength of different deep learning-based inverse design approaches has not been fully investigated.
Here, we benchmark three commonly used deep learning models in inverse design: Tandem networks, Variational Auto-Encoders, and Generative Adversarial Networks. We provide detailed comparisons in terms of their accuracy, diversity, and robustness. We find that tandem networks and Variational Auto-Encoders give the best accuracy, while Generative Adversarial Networks lead to the most diverse predictions.
Our findings could serve as a guideline for researchers to select the model that can best suit their design criteria and fabrication considerations. In addition, our code and data are publicly available, which could be used for future inverse design model development and benchmarking.
