TOPS-speed complex-valued convolutional accelerator for feature extraction and inference

Yunping Bai, Yifu Xu, Shifan Chen, Xiaotian Zhu, Shuai Wang, Sirui Huang, Yuhang Song, Yixuan Zheng, Zhihui Liu, Sim Tan, Roberto Morandotti, Sai T. Chu, Brent E. Little, David J. Moss (), Xingyuan Xu () and Kun Xu ()
Additional contact information
Yunping Bai: Beijing University of Posts and Telecommunications
Yifu Xu: Beijing University of Posts and Telecommunications
Shifan Chen: Beijing University of Posts and Telecommunications
Xiaotian Zhu: City University of Hong Kong
Shuai Wang: Beijing University of Posts and Telecommunications
Sirui Huang: Beijing University of Posts and Telecommunications
Yuhang Song: Beijing University of Posts and Telecommunications
Yixuan Zheng: Beijing University of Posts and Telecommunications
Zhihui Liu: Beijing University of Posts and Telecommunications
Sim Tan: Beihang University
Roberto Morandotti: INRS-Énergie, Matériaux et Télécommunications
Sai T. Chu: City University of Hong Kong
Brent E. Little: QXP Technology Inc.
David J. Moss: Swinburne University of Technology
Xingyuan Xu: Beijing University of Posts and Telecommunications
Kun Xu: Beijing University of Posts and Telecommunications

Nature Communications, 2025, vol. 16, issue 1, 1-13

Abstract: Abstract Complex-valued neural networks process both amplitude and phase information, in contrast to conventional artificial neural networks, achieving additive capabilities in recognizing phase-sensitive data inherent in wave-related phenomena. The ever-increasing data capacity and network scale place substantial demands on underlying computing hardware. In parallel with the successes and extensive efforts made in electronics, optical neuromorphic hardware is promising to achieve ultra-high computing performances due to its inherent analog architecture and wide bandwidth. Here, we report a complex-valued optical convolution accelerator operating at over 2 Tera operations per second (TOPS). With appropriately designed phasors we demonstrate its performance in the recognition of synthetic aperture radar (SAR) images captured by the Sentinel-1 satellite, which are inherently complex-valued and more intricate than what optical neural networks have previously processed. Experimental tests with 500 images yield an 83.8% accuracy, close to in-silico results. This approach facilitates feature extraction of phase-sensitive information, and represents a pivotal advance in artificial intelligence towards real-time, high-dimensional data analysis of complex and dynamic environments.

Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-55321-8 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-024-55321-8

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-024-55321-8

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().