Data enhanced iterative few-sample learning algorithm-based inverse design of 2D programmable chiral metamaterials

Abstract

A data enhanced iterative few-sample (DEIFS) algorithm is proposed to achieve the accurate and efficient inverse design of multi-shaped 2D chiral metamaterials. Specifically, three categories of 2D diffractive chiral structures with different geometrical parameters, including widths, separation spaces, bridge lengths, and gold lengths are studied utilising both the conventional rigorous coupled wave analysis (RCWA) approach and DEIFS algorithm, with the former approach assisting the training process for the latter. The DEIFS algorithm can be divided into two main stages, namely data enhancement and iterations. Firstly, some “pseudo data” are generated by a forward prediction network that can efficiently predict the circular dichroism (CD) response of 2D diffractive chiral metamaterials to reinforce the dataset after necessary denoising. Then, the algorithm uses the CD spectra and the predictions of parameters with smaller errors iteratively to achieve accurate values of the remaining parameters. Meanwhile, according to the impact of geometric parameters on the chiroptical response, a new functionality is added to interpret the experimental results of DEIFS algorithm from the perspective of data, improving the interpretability of the DEIFS. In this way, the DEIFS algorithm replaces the time-consuming iterative optimization process with a faster and simpler approach that achieves accurate inverse design with dataset whose amount is at least one to two orders of magnitude less than most previous deep learning methods, reducing the dependence on simulated spectra. Furthermore, the fast inverse design of multiple shaped metamaterials allows for different light manipulation, demonstrating excellent potentials in applications of optical coding and information processing. This work belongs to one of the first attempts to thoroughly characterize the flexibility, interpretability, and generalization ability of DEIFS algorithm in studying various chiroptical effects in metamaterials and accelerating the inverse design of hypersensitive photonic devices.

AI-Based Metamaterial Design

“…The outcome showed its potential for use as a continuous monitoring tool. The use of AI-based design of chiral plasmonic metamaterial has also been explored in prior studies aiming to develop personalized POC applications. − Such applications include DNA sensing, glucose quantification, bacteria detection, and the development of an electronic nose (Figure E) …”

Research progress of intelligent design of on-chip optical interconnection devices

“…2018年, Liu等 [117] 提出了一种"正、逆向串联神经 网络(tandem network) "的网络架构来解决"隐式 除了前文所述的工作之外, 2021年, Yeung等 [120] 还开发了一种基于全局深度学习的逆设计框架来 图 6 用来解决一些具体技术问题的神经网络架构 (a) "正、逆向串联"神经网络示意图以及利用该网络设计的多层膜系结构 [117] ; (b) 基于GA的深度神经网络 [118] ; (c) 利用少样本数据增强迭代算法优化得到的二维可编程手性超材料 [119] ; (d) 一种基于全局深 度学习的逆设计框架的训练和设计过程 [120] Fig. 6.…”

“…6. Neural network architectures used to solve some specific technical problems: (a) Schematic of the "forward and backward series" neural network and the multilayer structure designed by this network [117] ; (b) GA-based DNN [118] ; (c) two-dimensional programmable chiral metamaterial optimized by data enhanced iterative few-sample algorithm [119] ; (d) training and design process of an inverse design framework based on global deep learning [120] . 从而实现信息的一对多传递.…”

Spectral transfer-learning-based metasurface design assisted by complex-valued deep neural network

“…For example, the meta-atoms are treated as images using the transfer-learning model based on GoogLeNet-Inception-V3 and realize the classification of phase from 0 to 360 deg 35 . In addition to the transfer-learning-based method, data augmentation 36 and spectral scalability 37 were explored to reduce the dependence on data size, whereas previous works were limited to a fixed spectral range of the labeled data set. Once the range of the working waveband or the number of the sampling points changes, it is necessary to train a new model, and the training data set should be reprepared for this new task.…”