EUVIMEDEUVIMED entdecken
Crossref

AirNN: Over-the-Air Computation for Neural Networks via Reconfigurable Intelligent Surfaces

Sara Garcia Sanchez, Guillem Reus-Muns, Carlos Bocanegra, Yanyu Li, Ufuk Muncuk, Yousof Naderi, Yanzhi Wang, Stratis Ioannidis, Kaushik Roy Chowdhury

IEEE/ACM Transactions on Networking · 2023-12 · 31 (6) · 2470-2482

DOI: 10.1109/tnet.2022.3225883 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE/ACM Transactions on Networking, 2023-12. Verfasst von Sara Garcia Sanchez und 8 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: NSF AI Institute for Future Edge Networks and Distributed Intelligence, NSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Over-the-air analog computation allows offloading computation to the wireless environment through carefully constructed transmitted signals. In this paper, we design and implement the first-of-its-kind convolution that uses over-the-air computation and demonstrate it for inference tasks in a convolutional neural network (CNN). We engineer the ambient wireless propagation environment through reconfigurable intelligent surfaces (RIS) to design such an architecture, which we call ’AirNN’. AirNN leverages the physics of wave reflection to represent a digital convolution, an essential part of a CNN architecture, in the analog domain. In contrast to classical communication, where the receiver must react to the channel-induced transformation, generally represented as finite impulse response (FIR) filter, AirNN proactively creates the signal reflections to emulate specific FIR filters through RIS. AirNN involves two steps: first, the weights of the neurons in the CNN are drawn from a finite set of channel impulse responses (CIR) that correspond to realizable FIR filters. Second, each CIR is engineered through RIS, and reflected signals combine at the receiver to determine the output of the convolution. This paper presents a proof-of-concept of AirNN by experimentally demonstrating convolutions with over-the-air computation. We then validate the entire resulting CNN model accuracy via simulations for an example task of modulation classification.

Förderung

  • NSF AI Institute for Future Edge Networks and Distributed Intelligence
  • NSF

Zitieren

APA

Sanchez, S. G., Reus-Muns, G., Bocanegra, C., Li, Y., Muncuk, U., Naderi, Y., Wang, Y., Ioannidis, S., & Chowdhury, K. R. (2023). AirNN: Over-the-Air Computation for Neural Networks via Reconfigurable Intelligent Surfaces. IEEE/ACM Transactions on Networking, 31(6), 2470-2482. https://doi.org/10.1109/tnet.2022.3225883

Vancouver

Sanchez SG, Reus-Muns G, Bocanegra C, Li Y, Muncuk U, Naderi Y, et al. AirNN: Over-the-Air Computation for Neural Networks via Reconfigurable Intelligent Surfaces. IEEE/ACM Transactions on Networking. 2023;31(6):2470-2482. doi:10.1109/tnet.2022.3225883

BibTeX
@article{Sanchez2023,
  author = {Sanchez, Sara Garcia and Reus-Muns, Guillem and Bocanegra, Carlos and Li, Yanyu and Muncuk, Ufuk and Naderi, Yousof and Wang, Yanzhi and Ioannidis, Stratis and Chowdhury, Kaushik Roy},
  title = {AirNN: Over-the-Air Computation for Neural Networks via Reconfigurable Intelligent Surfaces},
  journal = {IEEE/ACM Transactions on Networking},
  year = {2023},
  volume = {31},
  number = {6},
  pages = {2470--2482},
  doi = {10.1109/tnet.2022.3225883}
}
Kostenlos starten →