Quantum-Classical Autoencoder Architectures for End-to-End Radio Communication

End-to-end radio communication needs to be optimized against noisy channel conditions and other distortion effects. This paper presents a novel concept, a set of hybrid quantum-classical autoencoder architectures with a comprehensive feasibility study using standard encoded radio signals, to evaluat...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE access Ročník 13; s. 82181 - 82192
Hlavní autoři: Tabi, Zsolt I., Bako, Bence, Nagy, Daniel T. R., Vaderna, Peter, Kallus, Zsofia, Haga, Peter, Zimboras, Zoltan
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Adaptation models
Autoencoders
Coding
Computer architecture
Encoding
Feasibility studies
Machine learning
Network design
Neural networks
Quadrature amplitude modulation
quantum autoencoder
Quantum circuit
Quantum machine learning
Radio communication
Radio communications
Radio signals
Random noise
Receivers
Receivers & amplifiers
Symbols
Transceivers
ISSN:2169-3536, 2169-3536
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:End-to-end radio communication needs to be optimized against noisy channel conditions and other distortion effects. This paper presents a novel concept, a set of hybrid quantum-classical autoencoder architectures with a comprehensive feasibility study using standard encoded radio signals, to evaluate quantum neural network design requirements for the radio context. The hybrid scenarios include single-sided, i.e., quantum encoder (transmitter) or quantum decoder (receiver), as well as fully quantum radio channel autoencoder (transmitter-receiver) systems. We provide detailed formulas for each scenario and validate our model through an extensive set of simulations. Our results demonstrate model robustness and adaptability. Supporting experiments are conducted utilizing 4 and 16 Quadrature Amplitude Modulation schemes and we expect that the model is adaptable to more general encoding schemes. We explore model performance against both additive white Gaussian noise and Rayleigh fading models. Our numerical findings highlight the importance of designing efficient quantum neural network architectures for meeting application performance constraints - including data re-uploading methods, encoding schemes, and core layer structures.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2025.3566207