Deep physical neural networks based on ultrafast nonlinear optics

Tatsuhiro Onodera; Logan G. Wright; Martin M. Stein; Tianyu Wang; Darren T. Schachter; Zoey Hu; Peter L. McMahon

doi:10.1117/12.2648103

17 March 2023 Deep physical neural networks based on ultrafast nonlinear optics

Tatsuhiro Onodera, Logan G. Wright, Martin M. Stein, Tianyu Wang, Darren T. Schachter, Zoey Hu, Peter L. McMahon

Proceedings Volume PC12438, AI and Optical Data Sciences IV; PC124380H (2023) https://doi.org/10.1117/12.2648103
Event: SPIE OPTO, 2023, San Francisco, California, United States

Abstract

Utilizing the input-output transformation of ultrafast nonlinear pulse propagation in quadratic media, we experimentally construct a multilayer physical neural network to perform both audio and handwritten image classification. We introduce a hybrid in-situ in-silico backpropagation algorithm, physics-aware training, that is resilient to the simulation-reality gap, to train physical neural networks. The methodology for constructing and training physical neural networks applies to generic complex physical systems. To demonstrate its generality, we also built and trained physical neural networks out of analog electronic circuits and multimode mechanical oscillators to perform image classification.

Conference Presentation

Citation Download Citation

Tatsuhiro Onodera, Logan G. Wright, Martin M. Stein, Tianyu Wang, Darren T. Schachter, Zoey Hu, and Peter L. McMahon "Deep physical neural networks based on ultrafast nonlinear optics", Proc. SPIE PC12438, AI and Optical Data Sciences IV, PC124380H (17 March 2023); https://doi.org/10.1117/12.2648103

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