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

View PDF HTML (experimental) 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, also known as Stacked Intelligent Metasurfaces (SIM), followed by a single reception radio-frequency chain. The front layer facing the XL MIMO channel consists of identical unit cells of a fixed NonLinear (NL) response, whereas 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 wireless systems. Comments: Invited Presentation at 2026 International Zurich Seminar on Information and Communication Subjects: Signal Processing (eess.SP); Emerging Technologies (cs.ET); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE) Cite as: arXiv:2601.17749 [eess.SP] (or arXiv:2601.17749v2 [eess.SP] for this version) https://doi.org/10.48550/arXiv.2601.17749 arXiv-issued DOI via DataCite Submission history From: Kyriakos Stylianopoulos [view email] [v1] Sun, 25 Jan 2026 08:47:20 UTC (914 KB) [v2] Wed, 8 Apr 2026 19:38:02 UTC (898 KB)