Over-The-Air Extreme Learning Machines with Nonlinear Stacked Intelligent Metasurfaces

arXiv:2608.27137 · eess.SP, cs.LG · Submitted 2026-08-27 · Read on arXiv

eess.SP, cs.LG

Submitted: 2026-08-27

Updated: 2026-08-27

Comments: To be presented at Int. Workshop Signal Process. Adv. Wireless Commun. (SPAWC), Athens, Greece, Sept. 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 13× in this paper · explained in 1 episode
• Extreme Learning Machine — 8× in this paper
• Activation Function — 5× in this paper · explained in 1 episode
• Machine Learning — 5× in this paper
• Edge Inference — 3× in this paper
• Feature Extraction — 2× in this paper · explained in 2 episodes
• Genetic Optimization — 2× in this paper
• Regularization — 2× in this paper · explained in 3 episodes
• Additive White Gaussian Noise — 1× in this paper
• Alignment — 1× in this paper · explained in 1 episode
• Amplitude Modulation — 1× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Multiple-Input Multiple-Output — 1× in this paper
• Projected Gradient Descent — 1× in this paper
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Signalto-Noise Ratio — 1× in this paper
• Steering — 1× in this paper · explained in 2 episodes
• Theoretical Guarantees — 1× in this paper · explained in 2 episodes
• Xtremely Large — 1× in this paper

Sources

• Over-the-Air Semantic Alignment with Stacked Intelligent Metasurfaces
• Universal Approximation with XL MIMO Systems: OTA Classification via Trainable Analog Combining
• Nonlinear Stacked Intelligent Surfaces for Wireless Systems
• Flexible Intelligent Layered Metasurfaces for Downlink Multi-user MISO Communications

Related papers

• What If They Took the Shot? A Hierarchical Bayesian Framework for Counterfactual Expected Goals
• Runtime Assurance Under Measurement Attack: Necessary and Sufficient Observability Conditions for Learned Control in Radio Access Networks
• Physics-Constrained Deep Learning Model for Contactless Blood Pressure Monitoring from Triaxial Bodyseismography
• SpellerSSL: Self-Supervised Learning with P300 Aggregation for Speller BCIs
• Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review
• Continuous Orthogonal Mode Decomposition: Haptic Signal Prediction in Tactile Internet