Metraipolis › archive › dc_196de766efe3

Radio-Frequency Convolutional Neural Networks — arXiv:2609.19279

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19279
License (as archived)
CC0-1.0
Archived
2026-10-10T04:08:34.727Z
SHA-256 of the archived text
49edce4c6d659bfcb244dfb90314f4757f09ae74912347c96f49b46a5255de52
Stable URL of this page
https://metraipolis.com/documento/dc_196de766efe3

How to cite

Radio-Frequency Convolutional Neural Networks — arXiv:2609.19279 — arXiv (en), https://arxiv.org/abs/2609.19279 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_196de766efe3 (Metraipolis archive dc_196de766efe3, sha256 49edce4c6d659bfcb244dfb90314f4757f09ae74912347c96f49b46a5255de52)
BibTeX
@misc{dc196de766efe3,
  title = {Radio-Frequency Convolutional Neural Networks — arXiv:2609.19279},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19279},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_196de766efe3; sha256 49edce4c6d659bfcb244dfb90314f4757f09ae74912347c96f49b46a5255de52},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19279. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Running artificial intelligence (AI) models directly on edge devices such as smartphones, wearables, and drones offers low latency, pervasive scalability, and data privacy, but these devices rarely carry the computing capability that modern neural networks demand. Edge accelerators have been developed in response, yet each adds computing hardware to devices already constrained in size, weight, power, and cost (SWaP-C). An alternative lies in what these devices already carry: the frequency mixer in every wireless radio multiplies signals in time, natively performing convolution in the frequency domain. Here we introduce radio-frequency convolutional neural networks (RF-CNNs), which repurpose existing communication hardware for CNN inference. Multi-channel convolutions are mapped onto frequency tones for a passive mixer to execute in a single pass. We experimentally demonstrate that RF-CNN runs deep CNNs up to 26.4 million parameters and nine layers from classification of wireless signals and images to controllable image generation, close to full-precision performance. Because the weights arrive over the air and the analog hardware is shared with communication, the edge device spends energy only on data preparation and readout-down to 0.72 femtojoules per multiply-accumulate, two orders of magnitude less than it would cost on an added digital processor. These results suggest that deployed wireless infrastructure can bring efficient, state-of-the-art AI inference to the billions of devices it already connects.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Emerging Technologies (cs.ET); Signal Processing (eess.SP); Applied Physics (physics.app-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.19279 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T03:48:18.241Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).