# Implementing Neural Networks Over-the-Air via Reconfigurable Intelligent Surfaces

arXiv: https://arxiv.org/abs/2508.01840 · HTML: https://mlsanity.com/paper/2508.01840/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2025.

## Built on by (most cited first, 7 of 7)

- [Integrating Stacked Intelligent Metasurfaces and Power Control for Dynamic Edge Inference via Over-The-Air Neural Networks](https://mlsanity.com/paper/2509.18906/) (2025)
- [Over-The-Air Extreme Learning Machines with XL Reception via Nonlinear Cascaded Metasurfaces](https://mlsanity.com/paper/2601.17749/) (2026)
- [Metasurfaces-Integrated Wireless Neural Networks for Lightweight Over-The-Air Edge Inference](https://mlsanity.com/paper/2602.19312/) (2026)
- [6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous Intelligence](https://mlsanity.com/paper/2605.01546/) (2026)
- [Analog RF Computing: A New Paradigm for Energy-Efficient Edge AI Over MU-MIMO Systems](https://mlsanity.com/paper/2605.14331/) (2026)
- [Multi-layer MIMO Relay as Deep Physical Neural Networks: Power Amplifiers as Activation Functions](https://mlsanity.com/paper/2607.18354/) (2026)
- [Over-The-Air Extreme Learning Machines with Nonlinear Stacked Intelligent Metasurfaces](https://mlsanity.com/paper/2608.27137/) (2026)

## Abstract (arXiv)

In this paper, we investigate reconfigurable intelligent surface (RIS)-aided multiple-input-multiple-output (MIMO) OAC systems designed to emulate the fully-connected (FC) layer of a neural network (NN) via analog OAC, where the RIS and the transceivers are jointly adjusted to engineer the ambient wireless propagation environment to emulate the weights of the target FC layer. We refer to this novel computational paradigm as AirFC. We first study the case in which the precoder, combiner, and RIS phase shift matrices are jointly optimized to minimize the mismatch between the OAC system and the target FC layer. To solve this non-convex optimization problem, we propose a low-complexity alternating optimization algorithm, where semi-closed-form/closed-form solutions for all optimization variables are derived. Next, we consider training of the system parameters using two distinct learning strategies, namely centralized training and distributed training. In the centralized training approach, training is performed at either the transmitter or the receiver, whichever possesses the channel state information (CSI), and the trained parameters are provided to the other terminal. In the distributed training approach, the transmitter and receiver iteratively update their parameters through back and forth transmissions by leveraging channel reciprocity, thereby avoiding CSI acquisition and significantly reducing computational complexity. Subsequently, we extend our analysis to a multi-RIS scenario by exploiting its spatial diversity gain to enhance the system performance. Simulation results show that the AirFC system realized by the RIS-aided MIMO configuration achieves satisfactory classification accuracy.