An efficient optical-based binary neural network hardware accelerator for harsh environments

Belal Jahannia; Jiachi Ye; Salem Altaleb; Chandraman Patil; Elham Heidari; Hamed Dalir

doi:10.1117/12.3003287

12 March 2024 An efficient optical-based binary neural network hardware accelerator for harsh environments

Belal Jahannia, Jiachi Ye, Salem Altaleb, Chandraman Patil, Elham Heidari, Hamed Dalir

Proceedings Volume 12891, Silicon Photonics XIX; 1289104 (2024) https://doi.org/10.1117/12.3003287
Event: SPIE OPTO, 2024, San Francisco, California, United States

Abstract

Binarized neural networks offer substantial reductions in memory and computational requirements compared to full precision networks. However, conventional CMOS-based hardware implementations still face challenges with resilience for deployment in harsh environments like space. This paper proposes an optical XOR-based accelerator for binarized neural networks to enable low power and resilient operation. The optical logic gates rely on wavelength-specific intensity propagation rather than absolute intensity levels. This provides inherent robustness against fabrication process variations and high energy particle strikes. Simulations of an optical hardware prototype for XNOR-Net show the accelerator achieves 1.2 μs latency and 3.2 mW power. The binarized network maintained 2-4% accuracy degradation compared to the full precision baseline on MNIST and CIFAR-10. The proposed optical accelerator enables efficient and resilient deployment of binarized neural networks for harsh environment applications like spacecraft and satellites.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Belal Jahannia, Jiachi Ye, Salem Altaleb, Chandraman Patil, Elham Heidari, and Hamed Dalir "An efficient optical-based binary neural network hardware accelerator for harsh environments", Proc. SPIE 12891, Silicon Photonics XIX, 1289104 (12 March 2024); https://doi.org/10.1117/12.3003287

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