Local loss function based single pass training of optical neural networks

Ilker Oguz; Junjie Ke; Qifei Wang; Feng Yang; Mustafa Yildirim; Niyazi Ulas Dinc; Jih-Liang Hsieh; Christophe Moser; Demetri Psaltis

doi:10.1117/12.3001573

13 March 2024 Local loss function based single pass training of optical neural networks

Ilker Oguz, Junjie Ke, Qifei Wang, Feng Yang, Mustafa Yildirim, Niyazi Ulas Dinc, Jih-Liang Hsieh, Christophe Moser, Demetri Psaltis

Author Affiliations +

Proceedings Volume PC12903, AI and Optical Data Sciences V; PC129030L (2024) https://doi.org/10.1117/12.3001573
Event: SPIE OPTO, 2024, San Francisco, California, United States

Abstract

As neural networks (NNs) become more capable, their computational resource requirements also increase exponentially. Optical systems can provide alternatives with higher parallelizability and lower energy consumption. However, the conventional training method, error backpropagation, is challenging to implement with these analog systems since it requires the characterization of the hardware. In contrast, the Forward-Forward Algorithm defines a local loss function for each layer and trains them sequentially without tracking the error gradient between different layers. In this study, we experimentally demonstrate the suitability of this approach for optical NNs by utilizing the multimode nonlinear propagation inside an optical fiber as a building block of the NN. Compared to the all-digital implementation, the optical NN achieves significantly higher classification accuracy while utilizing the optical system only one epoch per layer.

Conference Presentation

Citation Download Citation

Ilker Oguz, Junjie Ke, Qifei Wang, Feng Yang, Mustafa Yildirim, Niyazi Ulas Dinc, Jih-Liang Hsieh, Christophe Moser, and Demetri Psaltis "Local loss function based single pass training of optical neural networks", Proc. SPIE PC12903, AI and Optical Data Sciences V, PC129030L (13 March 2024); https://doi.org/10.1117/12.3001573

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

Education and training

Neural networks

Computer hardware

Detection and tracking algorithms

Channel projecting optics

Complex systems

Computing systems

Show All Keywords

Keywords/Phrases

Search In:

Publication Years