Design and experimental demonstration of a hardware-efficient integrated optical neural network

Chenghao Feng; Jiaqi Gu; Hanqing Zhu; David Z. Pan; Ray T. Chen

doi:10.1117/12.2610255

5 March 2022 Design and experimental demonstration of a hardware-efficient integrated optical neural network

Chenghao Feng, Jiaqi Gu, Hanqing Zhu, David Z. Pan, Ray T. Chen

Proceedings Volume PC12005, Smart Photonic and Optoelectronic Integrated Circuits 2022; PC120050E (2022) https://doi.org/10.1117/12.2610255
Event: SPIE OPTO, 2022, San Francisco, California, United States

Abstract

The optical neural network (ONN) is a promising neuromorphic framework for implementing deep learning tasks thanks to the key features of light, such as high parallelism, low latency, and low power consumption. As the size of deep neural networks (DNNs) continues to grow, so do the training and control difficulties of the corresponding photonic hardware accelerators. Therefore, it is essential to reduce the complexity of ONNs while maintaining accuracy. Here we propose an ONN architecture based on structured neural networks to reduce the optical component utilization as well as the chip footprint. The model complexity of our proposed ONN can be further optimized by incorporating current DNN pruning strategies. Meanwhile, a hardware-aware on-chip training flow is also proposed to improve the learnability, trainability, and robustness of our architecture. Finally, we experimentally demonstrate the reliability of this architecture with a programmable photonic neural chip and benchmarked its performance on multiple datasets.

Conference Presentation

Citation Download Citation

Chenghao Feng, Jiaqi Gu, Hanqing Zhu, David Z. Pan, and Ray T. Chen "Design and experimental demonstration of a hardware-efficient integrated optical neural network", Proc. SPIE PC12005, Smart Photonic and Optoelectronic Integrated Circuits 2022, PC120050E (5 March 2022); https://doi.org/10.1117/12.2610255

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