期刊
OPTICS COMMUNICATIONS
卷 481, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.optcom.2020.126513
关键词
Inverse design; Neural network; Nanophotonics
类别
资金
- National Key Research and Development Program of China [2018YFA0209000]
The study utilizes a tandem neural network with modified loss function for inverse design of nanophotonic devices, demonstrating high prediction accuracy and comparing different activation functions and loss functions for optimal scheme. The method can be easily applied to various cases to obtain design parameters instantly from device response curves.
The tandem neural network with a modified loss function is used to inversely design the nanophotonic device from a desired spectrum, to obtain the corresponding structural parameters. High prediction accuracy is demonstrated on the inverse design of grating coupler examples, etc. Different activation functions and loss functions used in the tandem network are compared to find the optimum scheme. The method can be readily applied to many other cases in order to obtain the design parameters instantaneously from the device response curves.
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