Noncoherent MIMO Codes Construction Using Autoencoders

ElMossallamy, Mohamed A.; Han, Zhu; Pan, Miao; Jäntti, Riku; Seddik, Karim G.; Li, Geoffrey Ye

doi:10.1109/globecom38437.2019.9013199

Cited by 8 publications

(13 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…greedy algorithm [3] and G 4,2 constellation [4] and the AE [7] constructing non-Grassmannian constellations are studied. In the simulation, we build neural networks on the DL framework Pytorch [10].…”

Section: Numerical Resultsmentioning

confidence: 99%

“…5) is adopted at the receiver. The label AE reference refers to the non-Grassmannian constellation learned by the AE in [7].…”

Section: Numerical Resultsmentioning

confidence: 99%

“…Thus, AE technique is known to be an approach to design constellations, as the output of transmitter neural network can be deemed as the transmitted symbols [6]. Authors in [7] adopt AE as a tool for optimizing constellation design in NC MIMO systems. Different from conventional methods designing Grassmannian constellations, the AE in [7] constructs non-Grassmannian constellations.…”

Section: Introductionmentioning

confidence: 99%

“…Authors in [7] adopt AE as a tool for optimizing constellation design in NC MIMO systems. Different from conventional methods designing Grassmannian constellations, the AE in [7] constructs non-Grassmannian constellations. The method in [7] shows better symbol error rate (SER) performance than conventional approaches when SNR is lower than 20dB, however it does not follow the theory of NC MIMO systems [2] and it is not rigorously justified to be applicable in NC MIMO systems.…”

Section: Introductionmentioning

confidence: 99%

“…Both Grassmannian constellations designed by conventional approaches [3], [4], [8] and the non-Grassmannian constellation [7] are studied. The proposed approach significantly outperforms all the state-of-the-art approaches at moderate to high SNRs.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Grassmannian Constellation Design for Noncoherent MIMO Systems Using Autoencoders

Fu,

Ruyet

2021

Preprint

View full text Add to dashboard Cite

In this letter, we propose an autoencoder (AE) for designing Grassmannian constellations in noncoherent (NC) multiple-input multiple-output (MIMO) systems. To guarantee the properties of Grassmannian constellations, the proposed AE constructs the transmitted symbols following an unitary space-time modulation. It penalizes the difference between input and output symbols in terms of cross entropy during the training, which is regarded as a generic optimization method. The constellations learned by the proposed AE have substantial symbol error rate (SER) performance gains compared to the non-Grassmannian constellations and conventionally constructed Grassmannian constellations in high SNR regime. The resulting Grassmannian constellation of the proposed AE achieves higher diversity than the non-Grassmannian constellation in i.i.d. Rayleigh channels. Moreover, the proposed approach can be adaptive to different channel statistics by training with corresponding channel realizations.

show abstract

Section: Numerical Resultsmentioning

confidence: 99%

“…5) is adopted at the receiver. The label AE reference refers to the non-Grassmannian constellation learned by the AE in [7].…”

Section: Numerical Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Grassmannian Constellation Design for Noncoherent MIMO Systems Using Autoencoders

Fu,

Ruyet

2021

Preprint

View full text Add to dashboard Cite

show abstract

Differential Unitary Space-Time Constellations From Spherical Codes

Attiah

Seddik

Gohary

2020

IEEE Wireless Commun. Lett.

View full text Add to dashboard Cite

Benchmarking and Interpreting End-to-End Learning of MIMO and Multi-User Communication

Song

Häger

Schröder

et al. 2022

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

End-to-end autoencoder (AE) learning has the potential of exceeding the performance of human-engineered transceivers and encoding schemes, without a priori knowledge of communication-theoretic principles. In this work, we aim to understand to what extent and for which scenarios this claim holds true when comparing with fair benchmarks. Our particular focus is on memoryless multiple-input multiple-output (MIMO) and multi-user (MU) systems. Four case studies are considered: two point-to-point (closed-loop and open-loop MIMO) and two MU scenarios (MIMO broadcast and interference channels).For the point-to-point scenarios, we explain some of the performance gains observed in prior work through the selection of improved baseline schemes that include geometric shaping as well as bit and power allocation. For the MIMO broadcast channel, we demonstrate the feasibility of a novel AE method with centralized learning and decentralized execution. Interestingly, the learned scheme performs close to nonlinear vector-perturbation precoding and significantly outperforms conventional zero-forcing. Lastly, we highlight potential pitfalls when interpreting learned communication schemes. In particular, we show that the AE for the considered interference channel learns to avoid interference, albeit in a rotated reference frame. After de-rotating the learned signal constellation of each user, the resulting scheme corresponds to conventional time sharing with geometric shaping.

show abstract

Noncoherent MIMO Codes Construction Using Autoencoders

Cited by 8 publications

References 22 publications

Grassmannian Constellation Design for Noncoherent MIMO Systems Using Autoencoders

Grassmannian Constellation Design for Noncoherent MIMO Systems Using Autoencoders

Differential Unitary Space-Time Constellations From Spherical Codes

Benchmarking and Interpreting End-to-End Learning of MIMO and Multi-User Communication

Contact Info

Product

Resources

About