All-dielectric metasurface designs enabled by deep neural networks

Sensong An; Clayton Fowler; Bowen Zheng; Mikhail Y. Shalaginov; Hong Tang; Hang Li; Jun Ding; Myungkoo Kang; Anuradha Murthy Agarwal; Clara Rivero-Baleine; Kathleen A. Richardson; Tian Gu; Juejun Hu; Hualiang Zhang

doi:10.1364/CLEO_QELS.2020.FW4B.8

All-dielectric metasurface designs enabled by deep neural networks

Sensong An
, Clayton Fowler
, Bowen Zheng
, Mikhail Y. Shalaginov
, Hong Tang
, Hang Li
, Jun Ding
, Myungkoo Kang
, Anuradha Murthy Agarwal
, Clara Rivero-Baleine
, Kathleen A. Richardson
, Tian Gu
, Juejun Hu
, Hualiang Zhang^*

^*此作品的通讯作者

通信与电子工程学院

University of Massachusetts Lowell
Massachusetts Institute of Technology
University of Central Florida
Lockheed Martin

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

We propose a deep learning design approach that significantly improves the design efficiency and accuracy over traditional trial-and-error methods that are currently in use to engineer metasurface-based devices.

源语言	英语
主期刊名	CLEO
主期刊副标题	QELS_Fundamental Science, CLEO_QELS 2020
出版商	Optica Publishing Group (formerly OSA)
ISBN（印刷版）	9781943580767
DOI	https://doi.org/10.1364/CLEO_QELS.2020.FW4B.8
出版状态	已出版 - 2020
活动	CLEO: QELS_Fundamental Science, CLEO_QELS 2020 - Washington, 美国期限: 10 5月 2020 → 15 5月 2020

出版系列

姓名	Optics InfoBase Conference Papers
卷	Part F182-CLEO-QELS 2020
ISSN（电子版）	2162-2701

会议

会议	CLEO: QELS_Fundamental Science, CLEO_QELS 2020
国家/地区	美国
市	Washington
时期	10/05/20 → 15/05/20

访问文件

10.1364/CLEO_QELS.2020.FW4B.8

其它文件与链接

链接到 Scopus 的出版物

引用此

An, S., Fowler, C., Zheng, B., Shalaginov, M. Y., Tang, H., Li, H., Ding, J., Kang, M., Agarwal, A. M., Rivero-Baleine, C., Richardson, K. A., Gu, T., Hu, J., & Zhang, H. (2020). All-dielectric metasurface designs enabled by deep neural networks. 在 CLEO: QELS_Fundamental Science, CLEO_QELS 2020 (Optics InfoBase Conference Papers; 卷 Part F182-CLEO-QELS 2020). Optica Publishing Group (formerly OSA). https://doi.org/10.1364/CLEO_QELS.2020.FW4B.8

@inproceedings{3f8ca8be05ef4f3faef9b731c7d40075,

title = "All-dielectric metasurface designs enabled by deep neural networks",

abstract = "We propose a deep learning design approach that significantly improves the design efficiency and accuracy over traditional trial-and-error methods that are currently in use to engineer metasurface-based devices.",

author = "Sensong An and Clayton Fowler and Bowen Zheng and Shalaginov, \{Mikhail Y.\} and Hong Tang and Hang Li and Jun Ding and Myungkoo Kang and Agarwal, \{Anuradha Murthy\} and Clara Rivero-Baleine and Richardson, \{Kathleen A.\} and Tian Gu and Juejun Hu and Hualiang Zhang",

note = "Publisher Copyright: CLEO 2020 {\textcopyright} OSA 2020.; CLEO: QELS\_Fundamental Science, CLEO\_QELS 2020 ; Conference date: 10-05-2020 Through 15-05-2020",

year = "2020",

doi = "10.1364/CLEO\_QELS.2020.FW4B.8",

language = "英语",

isbn = "9781943580767",

series = "Optics InfoBase Conference Papers",

publisher = "Optica Publishing Group (formerly OSA)",

booktitle = "CLEO",

address = "美国",

}

An, S, Fowler, C, Zheng, B, Shalaginov, MY, Tang, H, Li, H, Ding, J, Kang, M, Agarwal, AM, Rivero-Baleine, C, Richardson, KA, Gu, T, Hu, J & Zhang, H 2020, All-dielectric metasurface designs enabled by deep neural networks. 在 CLEO: QELS_Fundamental Science, CLEO_QELS 2020. Optics InfoBase Conference Papers, 卷 Part F182-CLEO-QELS 2020, Optica Publishing Group (formerly OSA), CLEO: QELS_Fundamental Science, CLEO_QELS 2020, Washington, 美国, 10/05/20. https://doi.org/10.1364/CLEO_QELS.2020.FW4B.8

TY - GEN

T1 - All-dielectric metasurface designs enabled by deep neural networks

AU - An, Sensong

AU - Fowler, Clayton

AU - Zheng, Bowen

AU - Shalaginov, Mikhail Y.

AU - Tang, Hong

AU - Li, Hang

AU - Ding, Jun

AU - Kang, Myungkoo

AU - Agarwal, Anuradha Murthy

AU - Rivero-Baleine, Clara

AU - Richardson, Kathleen A.

AU - Gu, Tian

AU - Hu, Juejun

AU - Zhang, Hualiang

PY - 2020

Y1 - 2020

N2 - We propose a deep learning design approach that significantly improves the design efficiency and accuracy over traditional trial-and-error methods that are currently in use to engineer metasurface-based devices.

AB - We propose a deep learning design approach that significantly improves the design efficiency and accuracy over traditional trial-and-error methods that are currently in use to engineer metasurface-based devices.

UR - https://www.scopus.com/pages/publications/85095450447

U2 - 10.1364/CLEO_QELS.2020.FW4B.8

DO - 10.1364/CLEO_QELS.2020.FW4B.8

M3 - 会议稿件

AN - SCOPUS:85095450447

SN - 9781943580767

T3 - Optics InfoBase Conference Papers

BT - CLEO

PB - Optica Publishing Group (formerly OSA)

T2 - CLEO: QELS_Fundamental Science, CLEO_QELS 2020

Y2 - 10 May 2020 through 15 May 2020

ER -

All-dielectric metasurface designs enabled by deep neural networks

摘要

出版系列

会议

访问文件

其它文件与链接

指纹

引用此