Uncertainty Qualification for Metasurface Design with Amendatory Bayesian Network,Laser & Photonics Reviews

当前位置： X-MOL 学术 › Laser Photonics Rev. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Uncertainty Qualification for Metasurface Design with Amendatory Bayesian Network
Laser & Photonics Reviews ( IF 9.8 ) Pub Date : 2023-02-07 , DOI: 10.1002/lpor.202200807
Jie Zhang _{1,

2,

3} , Chao Qian _{1,

2,

3} , Jieting Chen _{1,

2,

3} , Bei Wu ₄ , Hongsheng Chen _{1,

2,

3}

Affiliation

Having a prophetic ability to evaluate the uncertainty of deep learning is important to enable the critical reception of the output result. This is especially pronounced in the emerging domain of intelligent metasurfaces, due to the ubiquitous uncertainties from realistic fabrication and network modeling. Despite the great advancements that have mutated the design and working modality of metasurfaces, this enticing ability remains elusive. Here, a new paradigm to quantify the uncertainty in metasurface design is proposed by generalizing the Bayesian neural network. The uncertainty generally originates from the network model part and data part, the latter of which is imitated by the topologically-distorted encoding method. The conventional Bayesian neural network is revised by embedding physical-inspired elements to make it exclusive for metasurface design case. Taking a microwave metasurface as an example, such an approach is benchmarked by simultaneously yielding predicted results and specific uncertainty and also providing experimental reliability for different metasurface manufacturers. This work ushers in a fathomable tool to help users make better decisions for deep learning output, meriting other research domains of optics and materials science.

中文翻译：

修正贝叶斯网络超曲面设计的不确定性限定

具有评估深度学习不确定性的预测能力对于实现对输出结果的批判性接收很重要。由于现实制造和网络建模中普遍存在的不确定性，这在新兴的智能超表面领域尤为明显。尽管超表面的设计和工作方式发生了巨大的变化，但这种诱人的能力仍然难以捉摸。在这里，通过推广贝叶斯神经网络，提出了一种量化超表面设计不确定性的新范式。不确定性一般来源于网络模型部分和数据部分，后者是拓扑失真编码方法模仿的。通过嵌入受物理启发的元素来修改传统的贝叶斯神经网络，使其专用于超表面设计案例。以微波超表面为例，通过同时产生预测结果和特定不确定性以及为不同超表面制造商提供实验可靠性来对这种方法进行基准测试。这项工作开创了一种可理解的工具，帮助用户为深度学习输出做出更好的决策，值得光学和材料科学的其他研究领域。

更新日期：2023-02-07

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南