Early results on deep unfolded conjugate gradient‐based large‐scale MIMO detection
Abstract Deep learning (DL) is attracting considerable attention in the design of communication systems. This paper derives a deep unfolded conjugate gradient (CG) architecture for large‐scale multiple‐input multiple‐output detection. The proposed technique combines the advantages of a model‐driven...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-02-01
|
| Series: | IET Communications |
| Online Access: | https://doi.org/10.1049/cmu2.12076 |
| _version_ | 1798035566174928896 |
|---|---|
| author | Messaoud Ahmed Ouameur Daniel Massicotte |
| author_facet | Messaoud Ahmed Ouameur Daniel Massicotte |
| author_sort | Messaoud Ahmed Ouameur |
| collection | DOAJ |
| description | Abstract Deep learning (DL) is attracting considerable attention in the design of communication systems. This paper derives a deep unfolded conjugate gradient (CG) architecture for large‐scale multiple‐input multiple‐output detection. The proposed technique combines the advantages of a model‐driven approach in readily incorporating domain knowledge and deep learning in effective parameters learning. The parameters are trained via backpropagation over a data flow graph inspired from the iterative conjugate gradient method. We derive the closed‐form expressions for the gradients for parameters training and discuss early results on the performance in a statistically identical and independent distributed channel where the training overhead is considerably low. It is worth noting that the loss function is based on the residual error that is not an explicit function of the desired signal, which makes the proposed algorithm blind. As an initial framework, we will point to the inherent issues and future directions. |
| first_indexed | 2024-04-11T20:59:58Z |
| format | Article |
| id | doaj.art-30c3539781124edf98359671b7a1e39c |
| institution | Directory Open Access Journal |
| issn | 1751-8628 1751-8636 |
| language | English |
| last_indexed | 2024-04-11T20:59:58Z |
| publishDate | 2021-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Communications |
| spelling | doaj.art-30c3539781124edf98359671b7a1e39c2022-12-22T04:03:32ZengWileyIET Communications1751-86281751-86362021-02-0115343544410.1049/cmu2.12076Early results on deep unfolded conjugate gradient‐based large‐scale MIMO detectionMessaoud Ahmed Ouameur0Daniel Massicotte1Department of Electrical and Computer Engineering Laboratoire des Signaux et Systèmes Intégrés Chaire de recherche sur les signaux et l'intelligence des systèmes hautes performances Université du Québec à Trois‐Rivières Trois‐Rivières QC CanadaDepartment of Electrical and Computer Engineering Laboratoire des Signaux et Systèmes Intégrés Chaire de recherche sur les signaux et l'intelligence des systèmes hautes performances Université du Québec à Trois‐Rivières Trois‐Rivières QC CanadaAbstract Deep learning (DL) is attracting considerable attention in the design of communication systems. This paper derives a deep unfolded conjugate gradient (CG) architecture for large‐scale multiple‐input multiple‐output detection. The proposed technique combines the advantages of a model‐driven approach in readily incorporating domain knowledge and deep learning in effective parameters learning. The parameters are trained via backpropagation over a data flow graph inspired from the iterative conjugate gradient method. We derive the closed‐form expressions for the gradients for parameters training and discuss early results on the performance in a statistically identical and independent distributed channel where the training overhead is considerably low. It is worth noting that the loss function is based on the residual error that is not an explicit function of the desired signal, which makes the proposed algorithm blind. As an initial framework, we will point to the inherent issues and future directions.https://doi.org/10.1049/cmu2.12076 |
| spellingShingle | Messaoud Ahmed Ouameur Daniel Massicotte Early results on deep unfolded conjugate gradient‐based large‐scale MIMO detection IET Communications |
| title | Early results on deep unfolded conjugate gradient‐based large‐scale MIMO detection |
| title_full | Early results on deep unfolded conjugate gradient‐based large‐scale MIMO detection |
| title_fullStr | Early results on deep unfolded conjugate gradient‐based large‐scale MIMO detection |
| title_full_unstemmed | Early results on deep unfolded conjugate gradient‐based large‐scale MIMO detection |
| title_short | Early results on deep unfolded conjugate gradient‐based large‐scale MIMO detection |
| title_sort | early results on deep unfolded conjugate gradient based large scale mimo detection |
| url | https://doi.org/10.1049/cmu2.12076 |
| work_keys_str_mv | AT messaoudahmedouameur earlyresultsondeepunfoldedconjugategradientbasedlargescalemimodetection AT danielmassicotte earlyresultsondeepunfoldedconjugategradientbasedlargescalemimodetection |