Skip to Main content Skip to Navigation
Conference papers

Optimization and Analysis of Deep Unfolding Based Double Loop Turbo Equalizers

Abstract : This paper investigates the use of hybrid model-and-data-based deep learning on a recently proposed doubly-iterative turbo equalizer for handling inter-symbol interference (ISI) channel with single-carrier frequency domain equalization (SC-FDE). The receiver is obtained through a message-passing-based approximate Bayesian inference technique, known as expectation propagation (EP). Although this turbo-equalizer has been shown to behave asymptotically like maximum a posteriori (MAP) detection, finite-length numerical results suffer from drawbacks due to simplifying assumptions used during the modelling. Such limitations are partially mitigated by tuning heuristic hyper-parameters through robust learning algorithms. In this article, this strategy is further investigated with discussion on optimized parameters and with the use of an alternative loss function for training, or by adding further capabilities to adapt learned parameters to the channel state information.
Document type :
Conference papers
Complete list of metadata

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02950730
Contributor : Open Archive Toulouse Archive Ouverte (oatao) Connect in order to contact the contributor
Submitted on : Monday, September 28, 2020 - 11:31:14 AM
Last modification on : Wednesday, June 9, 2021 - 10:00:28 AM
Long-term archiving on: : Thursday, December 3, 2020 - 7:38:29 PM

File

sahin_26360.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02950730, version 1
  • OATAO : 26360

Citation

Serdar Sahin, Antonio Cipriano, Charly Poulliat. Optimization and Analysis of Deep Unfolding Based Double Loop Turbo Equalizers. Journées scientifiques d'URSI-France - Workshop: Réseaux du futur : 5G et au-delà (URSI-France 2020), Mar 2020, Palaiseau, France. pp.1-7. ⟨hal-02950730⟩

Share

Metrics

Record views

17

Files downloads

33