Programmable photonic neural engine with all-optical nonlinear activation and 40,000 connections
Science Advances · 2026-08-21 · 12 (34)
DOI: 10.1126/sciadv.aee9649 ↗At a glance
Journal article in Science Advances, published on 2026-08-21. Written by Hao Sun and 2 co-authors. Institution: Institut National de la Recherche Scientifique, Centre Énergie Matériaux Telecommunications (INRS-EMT), Montréal, QC H5A-1K6, Canada. 77 references. The full text is freely available in PubMed Central. Funded by: Natural Sciences and Engineering Research Council of Canada, Fonds de Recherche du Québec Nature et Technologies.
Abstract (original language)
The rapid advancement of artificial neural networks (ANNs) demands computational platforms with higher speed, energy efficiency, and scalability. Optical computing offers an appealing solution owing to the high-speed processing, inherent parallelism, and low energy consumption. However, existing optical neural network architectures face fundamental trade-offs between scalability, reconfigurability, and processing latency, constrained by the need to rely on electronic nonlinearities or fixed optical interconnections. Here, we report an end-to-end photonic neuromorphic engine that integrates all-optical nonlinearity into a loop-based, time-multiplexed photonic architecture. This approach enables all optical neurons to share common hardware, supporting enhanced connectivity and full reconfigurability with reduced latency. Implementations of four distinct network topologies, with a maximum of 40,000 optical connections for the single-layer perceptron, achieve digital-level inference accuracy and computational latency over two orders of magnitude shorter than state-of-the-art electronic processors, potentially paving the way for scalable, reconfigurable, and ultrafast optical artificial intelligence systems.
Authors and institutions
- Institut National de la Recherche Scientifique, Centre Énergie Matériaux Telecommunications (INRS-EMT), Montréal, QC H5A-1K6, Canada.
ORCID profiles: Hao Sun, José Azaña
Funding
- Natural Sciences and Engineering Research Council of Canada
- Fonds de Recherche du Québec Nature et Technologies
Cite
APA
Sun, H., Zhu, X., & Azaña, J. (2026). Programmable photonic neural engine with all-optical nonlinear activation and 40,000 connections. Science Advances, 12(34). https://doi.org/10.1126/sciadv.aee9649
Vancouver
Sun H, Zhu X, Azaña J. Programmable photonic neural engine with all-optical nonlinear activation and 40,000 connections. Science Advances. 2026;12(34). doi:10.1126/sciadv.aee9649
BibTeX
@article{Sun2026,
author = {Sun, Hao and Zhu, Xinyi and Azaña, José},
title = {Programmable photonic neural engine with all-optical nonlinear activation and 40,000 connections},
journal = {Science Advances},
year = {2026},
volume = {12},
number = {34},
doi = {10.1126/sciadv.aee9649}
}
EUVIMED