# Machine Intelligence on Wireless Edge Networks

arXiv: https://arxiv.org/abs/2506.12210 · HTML: https://mlsanity.com/paper/2506.12210/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 91 references that are in the map.
- First posted on arXiv 13 Jun 2025.

## Builds on (most cited first, 30 of 33)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [Split learning for health: Distributed deep learning without sharing raw patient data](https://mlsanity.com/paper/1812.00564/) (2018)
- [All-Optical Machine Learning Using Diffractive Deep Neural Networks](https://mlsanity.com/paper/1804.08711/) (2018)
- [Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems](https://mlsanity.com/paper/2104.13386/) (2021)
- [Photonics for artificial intelligence and neuromorphic computing](https://mlsanity.com/paper/2011.00111/) (2020)
- [Transformers without Normalization](https://mlsanity.com/paper/2503.10622/) (2025)
- [Neuromorphic Silicon Photonic Networks](https://mlsanity.com/paper/1611.02272/) (2016)
- [Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit](https://mlsanity.com/paper/2008.11659/) (2020)
- [PUMA: A Programmable Ultra-efficient Memristor-based Accelerator for Machine Learning Inference](https://mlsanity.com/paper/1901.10351/) (2019)
- [Training of Physical Neural Networks](https://mlsanity.com/paper/2406.03372/) (2024)
- [Experimentally realized in situ backpropagation for deep learning in nanophotonic neural networks](https://mlsanity.com/paper/2205.08501/) (2022)
- [Backpropagation-free Training of Deep Physical Neural Networks](https://mlsanity.com/paper/2304.11042/) (2023)
- [The physics of optical computing](https://mlsanity.com/paper/2308.00088/) (2023)
- [An optical neural network using less than 1 photon per multiplication](https://mlsanity.com/paper/2104.13467/) (2021)
- [Image sensing with multilayer, nonlinear optical neural networks](https://mlsanity.com/paper/2207.14293/) (2022)
- [A Survey on Over-the-Air Computation](https://mlsanity.com/paper/2210.11350/) (2022)
- [Nonlinear Processing with Linear Optics](https://mlsanity.com/paper/2307.08533/) (2023)
- [Single-Shot Optical Neural Network](https://mlsanity.com/paper/2205.09103/) (2022)
- [Fast offset corrected in-memory training](https://mlsanity.com/paper/2303.04721/) (2023)
- [Arbitrary control over multimode wave propagation for machine learning](https://mlsanity.com/paper/2402.17750/) (2024)
- [All-Photonic Artificial Neural Network Processor Via Non-linear Optics](https://mlsanity.com/paper/2205.08608/) (2022)
- [Computing Functions Over-the-Air Using Digital Modulations](https://mlsanity.com/paper/2303.00577/) (2023)
- [The Inherent Adversarial Robustness of Analog In-Memory Computing](https://mlsanity.com/paper/2411.07023/) (2024)
- [RF-Photonic Deep Learning Processor with Shannon-Limited Data Movement](https://mlsanity.com/paper/2207.06883/) (2022)
- [A Reconfigurable Linear RF Analog Processor for Realizing Microwave Artificial Neural Network](https://mlsanity.com/paper/2304.07378/) (2023)
- [Disaggregated Deep Learning via In-Physics Computing at Radio Frequency](https://mlsanity.com/paper/2504.17752/) (2025)
- [MultPIM: Fast Stateful Multiplication for Processing-in-Memory](https://mlsanity.com/paper/2108.13378/) (2021)

## Abstract (arXiv)

Machine intelligence on edge devices enables low-latency processing and improved privacy, but is often limited by the energy and delay of moving and converting data. Current systems frequently avoid local model storage by sending queries to a server, incurring uplink cost, network latency, and privacy risk. We present the opposite approach: broadcasting model weights to clients that perform inference locally using in-physics computation inside the radio receive chain. A base station transmits weights as radio frequency (RF) waveforms; the client encodes activations onto the waveform and computes the result using existing mixer and filter stages, RF components already present in billions of edge devices such as cellphones, eliminating repeated signal conversions and extra hardware. Analysis shows that thermal noise and nonlinearity create an optimal energy window for accurate analog inner products. Hardware-tailored training through a differentiable RF chain preserves accuracy within this regime. Circuit-informed simulations, consistent with a companion experiment, demonstrate reduced memory and conversion overhead while maintaining high accuracy in realistic wireless edge scenarios.