Machine learning frameworks for the inverse design of highly complicated multi-functional metasystems

Wenshan Cai

doi:10.1117/12.2567237

26 August 2020 Machine learning frameworks for the inverse design of highly complicated multi-functional metasystems

Wenshan Cai

Proceedings Volume 11460, Metamaterials, Metadevices, and Metasystems 2020; 1146017 (2020) https://doi.org/10.1117/12.2567237
Event: SPIE Nanoscience + Engineering, 2020, Online Only

Abstract

To fully unlock the capacity of engineered optical media, metadevices and metasystems are exploited with progressively greater complexity, including those with arbitrarily complicated topology, spatially variant building blocks, and multi-layered configurations. The astronomical degrees of freedom associated with such structures have obstructed effective design of them based on the conventional wisdom. Here we present a series of machine learning frameworks, consolidating deep neural networks, evolutionary strategy, and advanced patter generation methods for the inverse design of meta-structures in response to on-demand optical properties, with extensive case studies for multiplexed wavefront control, holography, and optical computing.

Conference Presentation

Citation Download Citation

Wenshan Cai "Machine learning frameworks for the inverse design of highly complicated multi-functional metasystems", Proc. SPIE 11460, Metamaterials, Metadevices, and Metasystems 2020, 1146017 (26 August 2020); https://doi.org/10.1117/12.2567237

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available