Deep Unfolding for Communications Systems: A Survey and Some New Directions

Alexios Balatsoukas-Stimming; Christoph Studer

doi:10.1109/SiPS47522.2019.9020494

Deep Unfolding for Communications Systems: A Survey and Some New Directions

Alexios Balatsoukas-Stimming, Christoph Studer

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

86 Citations (SciVal)

Abstract

Deep unfolding is a method of growing popularity that fuses iterative optimization algorithms with tools from neural networks to efficiently solve a range of tasks in machine learning, signal and image processing, and communication systems. This survey summarizes the principle of deep unfolding and discusses its recent use for communication systems with focus on detection and precoding in multi-Antenna (MIMO) wireless systems and belief propagation decoding of error-correcting codes. To showcase the efficacy and generality of deep unfolding, we describe a range of other tasks relevant to communication systems that can be solved using this emerging paradigm. We conclude the survey by outlining a list of open research problems and future research directions.

Original language	English
Title of host publication	2019 IEEE International Workshop on Signal Processing Systems, SiPS 2019
Publisher	Institute of Electrical and Electronics Engineers
Pages	266-271
Number of pages	6
ISBN (Electronic)	9781728119274
DOIs	https://doi.org/10.1109/SiPS47522.2019.9020494
Publication status	Published - Oct 2019
Event	33rd IEEE Workshop on Signal Processing Systems, SiPS 2019 - Nanjing, China Duration: 20 Oct 2019 → 23 Oct 2019 Conference number: 33

Conference

Conference	33rd IEEE Workshop on Signal Processing Systems, SiPS 2019
Abbreviated title	SiPS 2019
Country/Territory	China
City	Nanjing
Period	20/10/19 → 23/10/19

Keywords

channel coding
deep unfolding
Machine learning
massive MIMO

Access to Document

10.1109/SiPS47522.2019.9020494

Cite this

@inproceedings{40125555c0d941fa9ebb655a7e78e289,

title = "Deep Unfolding for Communications Systems: A Survey and Some New Directions",

abstract = "Deep unfolding is a method of growing popularity that fuses iterative optimization algorithms with tools from neural networks to efficiently solve a range of tasks in machine learning, signal and image processing, and communication systems. This survey summarizes the principle of deep unfolding and discusses its recent use for communication systems with focus on detection and precoding in multi-Antenna (MIMO) wireless systems and belief propagation decoding of error-correcting codes. To showcase the efficacy and generality of deep unfolding, we describe a range of other tasks relevant to communication systems that can be solved using this emerging paradigm. We conclude the survey by outlining a list of open research problems and future research directions.",

keywords = "channel coding, deep unfolding, Machine learning, massive MIMO",

author = "Alexios Balatsoukas-Stimming and Christoph Studer",

year = "2019",

month = oct,

doi = "10.1109/SiPS47522.2019.9020494",

language = "English",

pages = "266--271",

booktitle = "2019 IEEE International Workshop on Signal Processing Systems, SiPS 2019",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "33rd IEEE Workshop on Signal Processing Systems, SiPS 2019, SiPS 2019 ; Conference date: 20-10-2019 Through 23-10-2019",

}

Balatsoukas-Stimming, A & Studer, C 2019, Deep Unfolding for Communications Systems: A Survey and Some New Directions. in 2019 IEEE International Workshop on Signal Processing Systems, SiPS 2019., 9020494, Institute of Electrical and Electronics Engineers, pp. 266-271, 33rd IEEE Workshop on Signal Processing Systems, SiPS 2019, Nanjing, China, 20/10/19. https://doi.org/10.1109/SiPS47522.2019.9020494

Deep Unfolding for Communications Systems: A Survey and Some New Directions. / Balatsoukas-Stimming, Alexios; Studer, Christoph.
2019 IEEE International Workshop on Signal Processing Systems, SiPS 2019. Institute of Electrical and Electronics Engineers, 2019. p. 266-271 9020494.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Deep Unfolding for Communications Systems

T2 - 33rd IEEE Workshop on Signal Processing Systems, SiPS 2019

AU - Balatsoukas-Stimming, Alexios

AU - Studer, Christoph

N1 - Conference code: 33

PY - 2019/10

Y1 - 2019/10

N2 - Deep unfolding is a method of growing popularity that fuses iterative optimization algorithms with tools from neural networks to efficiently solve a range of tasks in machine learning, signal and image processing, and communication systems. This survey summarizes the principle of deep unfolding and discusses its recent use for communication systems with focus on detection and precoding in multi-Antenna (MIMO) wireless systems and belief propagation decoding of error-correcting codes. To showcase the efficacy and generality of deep unfolding, we describe a range of other tasks relevant to communication systems that can be solved using this emerging paradigm. We conclude the survey by outlining a list of open research problems and future research directions.

AB - Deep unfolding is a method of growing popularity that fuses iterative optimization algorithms with tools from neural networks to efficiently solve a range of tasks in machine learning, signal and image processing, and communication systems. This survey summarizes the principle of deep unfolding and discusses its recent use for communication systems with focus on detection and precoding in multi-Antenna (MIMO) wireless systems and belief propagation decoding of error-correcting codes. To showcase the efficacy and generality of deep unfolding, we describe a range of other tasks relevant to communication systems that can be solved using this emerging paradigm. We conclude the survey by outlining a list of open research problems and future research directions.

KW - channel coding

KW - deep unfolding

KW - Machine learning

KW - massive MIMO

UR - http://www.scopus.com/inward/record.url?scp=85082402493&partnerID=8YFLogxK

U2 - 10.1109/SiPS47522.2019.9020494

DO - 10.1109/SiPS47522.2019.9020494

M3 - Conference contribution

AN - SCOPUS:85082402493

SP - 266

EP - 271

BT - 2019 IEEE International Workshop on Signal Processing Systems, SiPS 2019

PB - Institute of Electrical and Electronics Engineers

Y2 - 20 October 2019 through 23 October 2019

ER -

Deep Unfolding for Communications Systems: A Survey and Some New Directions

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this