期刊
DIGITAL OPTICAL TECHNOLOGIES 2017
卷 10335, 期 -, 页码 -出版社
SPIE-INT SOC OPTICAL ENGINEERING
DOI: 10.1117/12.2270609
关键词
machine learning; Bayesian optimization; Gaussian process; 3D rigorous electromagnetic field simulations; finite-element methods
资金
- Senate of Berlin (IBB, ProFIT grant FI-SEQUR) [10160385]
- European Fund for Regional Development (EFRE)
- European Unions Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant [675745]
Numerical simulation of complex optical structures enables their optimization with respect to specific objectives. Often, optimization is done by multiple successive parameter scans, which are time consuming and computationally expensive. We employ here Bayesian optimization with Gaussian processes in order to automatize and speed up the optimization process. As a toy example, we demonstrate optimization of the shape of a free-form reflective meta surface such that it diffracts light into a specific diffraction order. For this example, we compare the performance of six different Bayesian optimization approaches with various acquisition functions and various kernels of the Gaussian process.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据