Disrupting the photonics innovation cycle with data- and physics-driven algorithms

Jonathan A. Fan

doi:10.1117/12.2595667

3 August 2021 Disrupting the photonics innovation cycle with data- and physics-driven algorithms

Jonathan A. Fan

Proceedings Volume 11795, Metamaterials, Metadevices, and Metasystems 2021; 117950F (2021) https://doi.org/10.1117/12.2595667
Event: SPIE Nanoscience + Engineering, 2021, San Diego, California, United States

Abstract

I will discuss the role of network architecture in the GLOnet inverse optimization platform, in which the global optimization process is reframed as the training of a generative neural network. I will show how a properly selected network architecture can smoothen the design space and how the architecture can be tailored based on the type and dimensionality of the design problem. I will also discuss new methods in which neural networks can serve as high speed surrogate Maxwell solvers capable of aiding the inverse design process. These hybrid physics- and data-driven concepts can apply to a broad range of nanophotonics systems.

Conference Presentation

Citation Download Citation

Jonathan A. Fan "Disrupting the photonics innovation cycle with data- and physics-driven algorithms", Proc. SPIE 11795, Metamaterials, Metadevices, and Metasystems 2021, 117950F (3 August 2021); https://doi.org/10.1117/12.2595667

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
PRESENTATION

WATCH
PRESENTATION SAVE TO MY LIBRARY

GET CITATION

KEYWORDS

Network architectures

Neural networks

Nanophotonics

RELATED CONTENT

Efficient design of structural parameters and materials of plasmonic fano...
Proceedings of SPIE (January 23 2023)

Assessing the design complexity of nanophotonic structures using machine learning
Proceedings of SPIE (January 01 1900)

Understanding the role of different design parameters in the response...
Proceedings of SPIE (January 01 1900)

Deep learning the design of optical components
Proceedings of SPIE (January 01 1900)

Neural network simulation on a reduced-mesh-of-trees organization
Proceedings of SPIE (July 01 1990)

Improved DUDnCNN-based noise reduction method for seismic data
Proceedings of SPIE (October 05 2021)

Research on data augmentation with generative adversarial networks in the...
Proceedings of SPIE (February 28 2024)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years