Deep learning assisted photonics

Zhaxylyk A. Kudyshev; Alexander V. Kildishev; Vladimir M. Shalaev; Alexandra Boltasseva

doi:10.1117/12.2567198

20 August 2020 Deep learning assisted photonics

Zhaxylyk A. Kudyshev, Alexander V. Kildishev, Vladimir M. Shalaev, Alexandra Boltasseva

Proceedings Volume 11461, Active Photonic Platforms XII; 114610C (2020) https://doi.org/10.1117/12.2567198
Event: SPIE Nanoscience + Engineering, 2020, Online Only

Abstract

The recent development of fabrication techniques and material platforms allows addressing various multi-constrained problems in many areas including on-chip circuitry, imaging, sensing, energy, and quantum information technology. However, these require advanced design development methods, which can go beyond conventional optimization. We will discuss recent and promising advances in the development of photonic components based on topology optimization. One of the main aspects of current work is expanding and streamlining a conventional meta-device design methodology to a global optimization space. Specifically, we will cover our recent efforts on coupling topology optimization techniques with deep generative algorithms for dielectric/plasmonic metastructure design development.

Conference Presentation

Citation Download Citation

Zhaxylyk A. Kudyshev, Alexander V. Kildishev, Vladimir M. Shalaev, and Alexandra Boltasseva "Deep learning assisted photonics", Proc. SPIE 11461, Active Photonic Platforms XII, 114610C (20 August 2020); https://doi.org/10.1117/12.2567198

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