Quantum Brain
← Back to papers

Hybrid Quantum-Classical Autoencoders for End-to-End Radio Communication

Zsolt I. Tabi, Bence Bakó, Dániel Nagy, Péter Vaderna, Zsófia Kallus, Péter Hága, Z. Zimborás·December 1, 2022·DOI: 10.1109/SEC54971.2022.00071
PhysicsEngineeringComputer Science

AI Breakdown

Get a structured breakdown of this paper — what it's about, the core idea, and key takeaways for the field.

Abstract

Quantum neural networks are emerging as poten-tial candidates to leverage noisy quantum processing units for applications. Here we introduce hybrid quantum-classical au-to encoders for end-to-end radio communication. In the physical layer of classical wireless systems, we study the performance of simulated architectures for standard encoded radio signals over a noisy channel. We implement a hybrid model, where a quantum decoder in the receiver works with a classical encoder in the transmitter part. Besides learning a latent space representation of the input symbols with good robustness against signal degradation, a generalized data re-uploading scheme for the qubit-based circuits allows to meet inference-time constraints of the application.

Related Research

Quantum Intelligence

Ask about quantum research, companies, or market developments.