Over-The-Air Extreme Learning Machines with XL Reception via Nonlinear Cascaded Metasurfaces

2026-01-25

AI Summary

This work explores the direct implementation of efficient, low-complexity machine learning inference at the wireless physical layer to support task-oriented communication. It proposes a MIMO architecture based on an ultra-large-scale programmable metasurface, which realizes an over-the-air extreme learning machine (ELM) composed of nonlinear cascaded diffractive layers followed by a tunable linear output layer. The system accomplishes end-to-end binary classification using only a single RF chain and enables closed-form training. Notably, this approach is the first to fully embed an ELM into the physical layer, leveraging a fixed nonlinear front-end and a reconfigurable linear back-end to approximate learned weights. Experimental results across multiple datasets and channel conditions demonstrate that the system achieves performance close to that of an ideal digital model, thereby validating the feasibility and potential of over-the-air intelligent inference.

Technology Category

• Machine Learning: Hardware-aware ML
• Humans and AI: Human-in-the-loop Machine Learning
• Multiagent Systems: Multiagent Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

The recently envisioned goal-oriented communications paradigm calls for the application of inference on wirelessly transferred data via Machine Learning (ML) tools. An emerging research direction deals with the realization of inference ML models directly in the physical layer of Multiple-Input Multiple-Output (MIMO) systems, which, however, entails certain significant challenges. In this paper, leveraging the technology of programmable MetaSurfaces (MSs), we present an eXtremely Large (XL) MIMO system that acts as an Extreme Learning Machine (ELM) performing binary classification tasks completely Over-The-Air (OTA), which can be trained in closed form. The proposed system comprises a receiver architecture consisting of densely parallel placed diffractive layers of XL MSs followed by a single reception radio-frequency chain. The front layer facing the MIMO channel consists of identical unit cells of a fixed NonLinear (NL) response, while the remaining layers of elements of tunable linear responses are utilized to approximate OTA the trained ELM weights. Our numerical investigations showcase that, in the XL regime of MS elements, the proposed XL-MIMO-ELM system achieves performance comparable to that of digital and idealized ML models across diverse datasets and wireless scenarios, thereby demonstrating the feasibility of embedding OTA learning capabilities into future communication systems.

Problem

• Over-The-Air inference
• Extreme Learning Machine
• XL-MIMO
• MetaSurfaces
• Physical-layer AI

Innovation

• Over-The-Air Learning
• Extreme Learning Machine
• Nonlinear Metasurfaces
• XL-MIMO
• Physical-Layer Inference