Optical computing for neural ordinary differential equations

Yun Zhao; Hang Chen; Min Lin; Haiou Zhang; Tao Yan; Xing Lin; Ruqi Huang; Qionghai Dai

doi:10.1117/12.3005767

21 December 2023 Optical computing for neural ordinary differential equations

Yun Zhao, Hang Chen, Min Lin, Haiou Zhang, Tao Yan, Xing Lin, Ruqi Huang, Qionghai Dai

Proceedings Volume 12966, AOPC 2023: AI in Optics and Photonics ; 129660P (2023) https://doi.org/10.1117/12.3005767
Event: Applied Optics and Photonics China 2023 (AOPC2023), 2023, Beijing, China

Abstract

Increasing the layer number can improve the model performance of on-chip optical neural networks (ONNs). However, this results in larger integrated photonic chip areas due to the successive cascading of network hidden layers. We introduce a novel architecture for optical computing based on neural ordinary differential equations (ODEs) that employing optical ODE solvers to parameterize the continuous dynamics of hidden layers. The architecture comprises ONNs followed by a photonic integrator and an optical feedback loop, which can be configured to represent residual neural networks (ResNets) and implement the function of recurrent neural networks with effectively reduced chip area occupancy. For the interference-based optoelectronic nonlinear hidden layer, we demonstrate that the single hidden layer architecture can achieve approximately the same accuracy as the two-layer optical ResNets in image classification tasks. Furthermore, the architecture improves the model classification accuracy for the diffraction-based all-optical linear hidden layer. We also utilize the time-dependent dynamics property of architecture for trajectory prediction with high accuracy.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yun Zhao, Hang Chen, Min Lin, Haiou Zhang, Tao Yan, Xing Lin, Ruqi Huang, and Qionghai Dai "Optical computing for neural ordinary differential equations", Proc. SPIE 12966, AOPC 2023: AI in Optics and Photonics , 129660P (21 December 2023); https://doi.org/10.1117/12.3005767

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