EUVIMEDEUVIMED entdecken
Open Access

Disaggregated machine learning via in-physics computing at radio frequency

Zhihui Gao iD, Sri Krishna Vadlamani iD, Kfir Sulimany iD, Dirk Englund iD, Tingjun Chen iD

Science Advances · 09.01.2026 · 12 (2)

DOI: 10.1126/sciadv.adz0817 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 09.01.2026. Verfasst von Zhihui Gao und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Science Foundation, Defense Sciences Office, DARPA, Zuckerman STEM Leadership Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern edge devices, such as cameras, drones, and internet-of-things nodes, rely on machine learning to enable a wide range of intelligent applications. However, deploying machine learning models directly on the often resource-constrained edge devices demands substantial memory footprints and computational power for real-time inference using traditional digital computing architectures. In this paper, we present WISE, computing architecture for wireless edge networks with two key innovations: disaggregated model access via over-the-air wireless broadcasting for simultaneous inference on multiple edge devices, and in-physics computation of general complex-valued matrix-vector multiplications directly at radio frequency driven by a single frequency mixer. Using a software-defined radio platform, WISE achieves 95.7% image classification accuracy (97.2% audio classification accuracy) with ultralow energy consumption of 6.0 fJ/MAC (2.8 fJ/MAC), which is more than 10× improvement compared to traditional digital computing, e.g., on modern GPUs.

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA.
  • Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.

ORCID-Profile: Zhihui Gao, Sri Krishna Vadlamani, Kfir Sulimany, Dirk Englund, Tingjun Chen

Förderung

  • National Science Foundation
  • Defense Sciences Office, DARPA
  • Zuckerman STEM Leadership Program
  • Israeli Council for Higher Education

Zitieren

APA

Gao, Z., Vadlamani, S. K., Sulimany, K., Englund, D., & Chen, T. (2026). Disaggregated machine learning via in-physics computing at radio frequency. Science Advances, 12(2). https://doi.org/10.1126/sciadv.adz0817

Vancouver

Gao Z, Vadlamani SK, Sulimany K, Englund D, Chen T. Disaggregated machine learning via in-physics computing at radio frequency. Science Advances. 2026;12(2). doi:10.1126/sciadv.adz0817

BibTeX
@article{Gao2026,
  author = {Gao, Zhihui and Vadlamani, Sri Krishna and Sulimany, Kfir and Englund, Dirk and Chen, Tingjun},
  title = {Disaggregated machine learning via in-physics computing at radio frequency},
  journal = {Science Advances},
  year = {2026},
  volume = {12},
  number = {2},
  doi = {10.1126/sciadv.adz0817}
}
Kostenlos starten →