aiqbench analysis
This research proposes RF-CNNs, a novel architecture that leverages the inherent mixing properties of standard wireless radio hardware to perform convolution operations natively in the frequency domain. By repurposing existing communication mixers instead of adding dedicated digital accelerators, the method achieves deep neural network inference with energy efficiency two orders of magnitude lower than conventional edge processors. This approach effectively bridges the gap between AI model complexity and the strict size, weight, power, and cost constraints of ubiquitous edge devices like smartphones and drones.
Radio-Frequency Convolutional Neural Networks
arXiv:2609.19279v1 Announce Type: new Abstract: 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.
Abstract: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.
15 pages, 4 figures. Supplementary Information: 50 pages, 31 figures, 1 table
Machine Learning (cs.LG); Emerging Technologies (cs.ET); Signal Processing (eess.SP); Applied Physics (physics.app-ph)
arXiv:2609.19279 [cs.LG]
(or arXiv:2609.19279v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.19279 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 331 words
Related coverage
Compact convolutional neural networks for AI-based drone detection system
arXiv · Jul 21, 2026
RF Fingerprinting of DSP Implementations using Machine Learning: An Over-the-Air Case Study
arXiv · Oct 14, 2026
Neural Network Verification for Deep Joint Source-Channel Coding
arXiv · Oct 10, 2026
A comparison between ceiling-mounted FMCW, IR-UWB and Wi-Fi radar for in-bedroom human activity monitoring and sleep interruption detection
arXiv · Aug 21, 2026