Physical Layer-aware Digital-Analog Co-Design for Photonic Convolution Neural Network

Photonic convolution neural network (CNN) has shown tremendous capability to provide Tera-level operations/sec (OPS) for streaming object detection with ultra-low energy consumption. However, due to the nature of analog photonic computing which is constrained by accumulated noise from various source...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in quantum electronics 2023-11, Vol.29 (6: Photonic Signal Processing), p.1-9
Main Authors: Jiang, Yue, Zhang, Wenjia, Liu, Xuying, Zhu, Wenyu, Du, Jiangbin, He, Zuyuan
Format: Article
Language:English
Subjects:
Adaptive optics
Artificial intelligence
Artificial neural networks
Co-design
Computation
Convolution
Energy consumption
Graphics processing units
Image edge detection
Learning
Object recognition
Optical Computing
Optical imaging
Photonic Convolutional Neural Network
Photonics
Physical layer
Tensors
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Photonic convolution neural network (CNN) has shown tremendous capability to provide Tera-level operations/sec (OPS) for streaming object detection with ultra-low energy consumption. However, due to the nature of analog photonic computing which is constrained by accumulated noise from various sources, its physical operating precision is significantly lower than that of electronic artificial intelligence (AI) accelerators powered by tensor processing unit (TPU) and graphic processing unit (GPU). In this paper, we propose a robust digital-analog co-designed photonic CNN using error learning and Kirsch edge enhancement. Experimental results show that, nearly 96.1% recognition accuracy, compared with 34.2% in baseline photonic CNN, can be achieved at global 2-bit precision through physical error learning in dense layer and edge enhancement by photonic Kirsch operator. The proposed photonic CNN architecture is promising to provide 10 Tera-OPS scale computing speed deployed by the state of art PAM-4 optical modules with high energy efficiency.
ISSN:1077-260X
1558-4542
DOI:10.1109/JSTQE.2023.3279586