面向复杂元表面设计的SUTD-PRCM数据集和神经结构搜索方法
SUTD-PRCM Dataset and Neural Architecture Search Approach for Complex Metasurface Design
摘要：
超颖表面因其在电磁波操控方面的多样性而受到广泛关注。满足具有非线性约束的多个目标的高级设计已经激励研究人员使用机器学习（ML）技术，如深度学习（DL）来加速元表面的设计。对于元表面，如果没有在图像分类等许多学科中使用的通用但复杂的数据集，就很难在不同的ML模型之间进行定量比较。许多研究都是针对相对受限的数据集，这些数据集仅限于元表面中指定的模式或形状。在本文中，我们提出了我们的SUTD极化反射复杂元表面（SUTD-PRCM）数据集，其中包含大约260，000个从电磁模拟创建的复杂元表面样本，并已用于基准我们的DL模型。元表面图案被分成不同的类以促进不同程度的复杂性，这涉及识别和利用图案与电磁响应之间的关系，该关系可以在使用不同DL模型时进行比较。随着SUTD-PRCM数据集的发布，我们希望它将有助于对ML社区中开发的现有或未来DL模型进行基准测试。我们还提出了一个分类问题，是很少遇到的，并应用神经架构搜索有一个潜在的修改的神经架构，这将提高DL模型的预测初步了解。我们的发现表明，卷积堆叠不再是神经架构的主导元素，这意味着低级特征优于传统的深层高级特征，从而解释了为什么基于深度卷积神经网络的模型在我们的数据集中表现不佳。
英文摘要：
Metasurfaces have received a lot of attentions recently due to their versatile capability in manipulating electromagnetic wave. Advanced designs to satisfy multiple objectives with non-linear constraints have motivated researchers in using machine learning (ML) techniques like deep learning (DL) for accelerated design of metasurfaces. For metasurfaces, it is difficult to make quantitative comparisons between different ML models without having a common and yet complex dataset used in many disciplines like image classification. Many studies were directed to a relatively constrained datasets that are limited to specified patterns or shapes in metasurfaces. In this paper, we present our SUTD polarized reflection of complex metasurfaces (SUTD-PRCM) dataset, which contains approximately 260,000 samples of complex metasurfaces created from electromagnetic simulation, and it has been used to benchmark our DL models. The metasurface patterns are divided into different classes to facilitate different degree of complexity, which involves identifying and exploiting the relationship between the patterns and the electromagnetic responses that can be compared in using different DL models. With the release of this SUTD-PRCM dataset, we hope that it will be useful for benchmarking existing or future DL models developed in the ML community. We also propose a classification problem that is less encountered and apply neural architecture search to have a preliminary understanding of potential modification to the neural architecture that will improve the prediction by DL models. Our finding shows that convolution stacking is not the dominant element of the neural architecture anymore, which implies that low-level features are preferred over the traditional deep hierarchical high-level features thus explains why deep convolutional neural network based models are not performing well in our dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
