AI and Optical Data Sciences III最新文献_第3页

Enhancing adjoint optimization-based photonics inverse design with explainable machine learning 利用可解释的机器学习增强基于伴随优化的光子逆设计

AI and Optical Data Sciences III Pub Date : 2022-03-09 DOI: 10.1117/12.2610548

Christopher Yeung, David Ho, Benjamin Pham, Katherine T Fountaine, A. Raman

{"title":"Enhancing adjoint optimization-based photonics inverse design with explainable machine learning","authors":"Christopher Yeung, David Ho, Benjamin Pham, Katherine T Fountaine, A. Raman","doi":"10.1117/12.2610548","DOIUrl":"https://doi.org/10.1117/12.2610548","url":null,"abstract":"A fundamental challenge in the design of photonic devices and electromagnetic structures more generally is the optimization of their overall architecture to achieve a desired response. To this end, topology or shape optimizers based on the adjoint variables method have been widely adopted due to their high computational efficiency and ability to create complex freeform geometries. However, the functional understanding of such freeform structures remains black box. Moreover, unless a design space of high-performance devices is known in advance, such gradient-based optimizers can get trapped in local minima, limiting performance achievable through this inverse design process. To elucidate the relationships between device performance and nanoscale structuring, while mitigating the effects of local minima trapping, we present an inverse design framework that combines adjoint optimization, automated machine learning (AutoML), and explainable artificial intelligence (XAI). Integrated with a numerical electromagnetics simulation method, our framework reveals structural contributions towards a figure-of-merit (FOM) of interest, then leverages this information to minimize the FOM further than that obtained through adjoint optimization alone, overcoming local minima. We demonstrate our framework in the context of waveguide design and achieve between 43% and 74% increases in device performance relative to state-of-the-art adjoint optimization-based inverse design across a range of telecom wavelengths. Results of this work thus highlight machine learning strategies that can substantially extend and improve the capabilities of a conventional, optimization-based inverse design algorithm while revealing deeper insights into the algorithm’s designs.","PeriodicalId":120461,"journal":{"name":"AI and Optical Data Sciences III","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128301274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Diffractive optical networks with scale, shift, and rotation invariance 具有尺度、位移和旋转不变性的衍射光网络

AI and Optical Data Sciences III Pub Date : 2022-03-09 DOI: 10.1117/12.2609500

Deniz Mengu, Y. Rivenson, Aydogan Ozcan

引用次数: 0

Miniaturized integrative polarizer system for autonomous glare removal 用于自动消除眩光的小型化综合偏光系统

AI and Optical Data Sciences III Pub Date : 2022-03-09 DOI: 10.1117/12.2609936

Henry Do, Xintao Zhao, Ancheng Da, J. Gregg, Yunbo Liu, S. Lee

引用次数: 0

Advancing diffractive network-based image classification by ensemble learning 基于集成学习的衍射网络图像分类

AI and Optical Data Sciences III Pub Date : 2022-03-09 DOI: 10.1117/12.2608016

Md. Sadman Sakib Rahman, Jingxi Li, Deniz Mengu, Y. Rivenson, Aydogan Ozcan

引用次数: 0

High speed 2D-photodetector array device and its application for optical signal processing 高速二维光电探测器阵列及其在光信号处理中的应用

AI and Optical Data Sciences III Pub Date : 2022-03-09 DOI: 10.1117/12.2607239

T. Umezawa, Y. Yoshida, A. Kanno, N. Yamamoto

引用次数: 0

Physics-informed neural network for predicting electric field distributions and permittivities of circular split-ring resonators 用于预测圆形劈环谐振器电场分布和介电常数的物理信息神经网络

AI and Optical Data Sciences III Pub Date : 2022-03-07 DOI: 10.1117/12.2609446

P. Pillai, A. Chaudhuri, B. Rai, P. Pal

引用次数: 0

Tuneable spin-glass optical simulator based on multiple light scattering 基于多重光散射的可调谐自旋玻璃光学模拟器

AI and Optical Data Sciences III Pub Date : 2022-03-07 DOI: 10.1117/12.2625600

L. Delloye, G. Jacucci, D. Pierangeli, M. Rafayelyan, C. Conti, S. Gigan

引用次数: 0