arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.03431physics.opticsphysics.comp-ph
收藏

通过深度学习实现具有灵活设计目标的逆向设计:调整纳米球体的电磁多极散射

Inverse design with flexible design targets via deep learning: Tailoring of electric and magnetic multipole scattering from nano-spheres

Ana Estrada-Real, Abdourahman Khaireh-Walieh, Bernhard Urbaszek, Peter R. Wiecha

摘要:

深度学习是纳米光学逆向设计的一种有前途的超快速方法,但尽管该领域发展迅速,数据集生成的计算成本以及训练过程本身仍然是一个主要瓶颈。这是特别不方便的,因为需要生成新的数据,并且需要训练新的网络以用于问题的任何修改。我们提出了一种技术,允许训练一个单一的神经网络上广泛的设计目标,而无需任何重新训练。我们的方法的关键思想是丰富现有的数据与随机的“感兴趣的区域”(ROI)标签。在这种ROI装饰数据上训练的模型能够对广泛的物理目标进行操作,同时它学会将其设计工作集中在用户定义的ROI上,而忽略物理域的其余部分。我们展示了一个串联网络的设计上的电和磁偶极子和四极散射在一个广泛的光谱范围内的介电核壳纳米球的训练方法。该网络学习定制非常独特,灵活的设计目标,如由于窄光谱窗口中的特定多极子而产生的散射。改变设计问题不需要任何重新训练。我们的方法非常通用,可以直接用于现有的数据集。它可以直接应用于其他网络体系结构和问题。

英文摘要:

Deep learning is a promising, ultra-fast approach for inverse design in nano-optics, but despite fast advancement of the field, the computational cost of dataset generation, as well as of the training procedure itself remains a major bottleneck. This is particularly inconvenient because new data need to be generated and a new network needs to be trained for any modification of the problem. We propose a technique that allows to train a single neural network on a broad range of design targets without any re-training. The key idea of our method is to enrich existing data with random "regions of interest" (ROI) labels. A model trained on such ROI-decorated data becomes capable to operate on a broad range of physical targets, while it learns to focus its design effort on a user-defined ROI, ignoring the rest of the physical domain. We demonstrate the method by training a tandem-network on the design of dielectric core-shell nano-spheres for electric and magnetic dipole and quadrupole scattering over a broad spectral range. The network learns to tailor very distinct, flexible design targets like scattering due to specific multipoles in narrow spectral windows. Varying the design problem does not require any re-training. Our approach is very general and can be directly used with existing datasets. It can be straightforwardly applied to other network architectures and problems.

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。

↑