A Universal Neural Receiver that Learns at the Speed of Wireless

2026-02-17

AI Summary

This work proposes a universal neural receiver architecture to overcome the limitations of conventional model-based wireless receivers, which struggle in dynamic interference environments, and offline-trained AI methods, which fail to meet sub-millisecond real-time requirements. By leveraging convolutional modeling, the approach decouples deconvolution tasks from specific channel characteristics and integrates domain knowledge to directly configure network weights—eliminating the need for large-scale offline training. The resulting design enables real-time adaptation to arbitrary spectra and waveforms, achieving unified, efficient processing across frequency bands and modulation schemes. This significantly enhances spectral efficiency, advances the development of AI-native physical layers, and reduces the complexity of waveform selection in wireless standards.

Technology Category

• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

Today we design wireless networks using mathematical models that govern communication in different propagation environments. We rely on measurement campaigns to deliver parametrized propagation models, and on the 3GPP standards process to optimize model-based performance, but as wireless networks become more complex this model-based approach is losing ground. Mobile Network Operators (MNOs) are counting on Artificial Intelligence (AI) to transform wireless by increasing spectral efficiency, reducing signaling overhead, and enabling continuous network innovation through software upgrades. They may also be interested in new use cases like integrated sensing and communications (ISAC). All we need is an AI-native physical layer, so why not simply tailor the offline AI algorithms that have revolutionized image and natural language processing to the wireless domain? We argue that these algorithms rely on off-line training that is precluded by the sub-millisecond speeds at which the wireless interference environment changes. We present an alternative architecture, a universal neural receiver based on convolution, which governs transmit and receive signal processing of any signal in any part of the wireless spectrum. Our neural receiver is designed to invert convolution, and we separate the question of which convolution to invert from the actual deconvolution. The neural network that performs deconvolution is very simple, and we configure this network by setting weights based on domain knowledge. By telling our neural network what we know, we avoid extensive offline training. By developing a universal receiver, we hope to simplify discussions about the proper choice of waveform for different use cases in the international standards. Since the receiver architecture is largely independent of technologies introduced at the base station, we hope to increase the rate of innovation in wireless.

Problem

• wireless communication
• neural receiver
• offline training
• physical layer
• real-time adaptation

Innovation

• universal neural receiver
• real-time learning
• deconvolution
• AI-native physical layer
• domain-knowledge-based weight configuration