Data-Driven Symbol Detection Via Model-Based Machine Learning

Nariman Farsad; Nir Shlezinger; Andrea J Goldsmith; Yonina C Eldar

doi:https://doi.org/10.1109/SSP49050.2021.9513859

Data-Driven Symbol Detection Via Model-Based Machine Learning

Nariman Farsad, Nir Shlezinger, Andrea J Goldsmith, Yonina C Eldar

Department of Electrical & Computer Engineering

Ben-Gurion University of the Negev

Research output: Contribution to conference › Paper › peer-review

Abstract

We present a data-driven framework to symbol detection design that combines machine learning (ML) and model-based algorithms. The resulting data-driven receivers are most suitable for systems where the underlying channel models are poorly understood, highly complex, or do not well-capture the underlying physics. Our approach is unique in that it only replaces the channel-model-based computations with dedicated neural networks that can be trained from a small amount of data, while keeping the general algorithm intact. Our results demonstrate that these techniques can yield performance close to that of model-based algorithms with perfect model knowledge without knowing the exact channel model or state.

Original language	English
Pages	571-575
Number of pages	5
DOIs	https://doi.org/10.1109/SSP49050.2021.9513859
State	Published - 11 Jul 2021
Event	21st IEEE Statistical Signal Processing Workshop, SSP 2021 - Virtual, Rio de Janeiro, Brazil Duration: 11 Jul 2021 → 14 Jul 2021

Conference

Conference	21st IEEE Statistical Signal Processing Workshop, SSP 2021
Country/Territory	Brazil
City	Virtual, Rio de Janeiro
Period	11/07/21 → 14/07/21

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering
Applied Mathematics
Signal Processing
Computer Science Applications

Access to Document

https://doi.org/10.1109/SSP49050.2021.9513859

Cite this

@conference{2452b9c66aec499584ac235cb8abe26a,

title = "Data-Driven Symbol Detection Via Model-Based Machine Learning",

abstract = "We present a data-driven framework to symbol detection design that combines machine learning (ML) and model-based algorithms. The resulting data-driven receivers are most suitable for systems where the underlying channel models are poorly understood, highly complex, or do not well-capture the underlying physics. Our approach is unique in that it only replaces the channel-model-based computations with dedicated neural networks that can be trained from a small amount of data, while keeping the general algorithm intact. Our results demonstrate that these techniques can yield performance close to that of model-based algorithms with perfect model knowledge without knowing the exact channel model or state. ",

author = "Nariman Farsad and Nir Shlezinger and Goldsmith, {Andrea J} and Eldar, {Yonina C}",

note = "Funding Information: ∗This work was supported in part by the US - Israel Binational Science Foundation under grant No. 2026094, by the Israel Science Foundation under grant No. 0100101, by the Office of the Naval Research under grant No. 18-1-2191, and by the Discovery Grant from the Natural Sciences and Engineering Research Council of Canada (NSERC) and Canada Foundation for Innovation (CFI), John R. Evans Leader Fund. Publisher Copyright: {\textcopyright} 2021 IEEE.; 21st IEEE Statistical Signal Processing Workshop, SSP 2021 ; Conference date: 11-07-2021 Through 14-07-2021",

year = "2021",

month = jul,

day = "11",

doi = "https://doi.org/10.1109/SSP49050.2021.9513859",

language = "English",

pages = "571--575",

}

TY - CONF

T1 - Data-Driven Symbol Detection Via Model-Based Machine Learning

AU - Farsad, Nariman

AU - Shlezinger, Nir

AU - Goldsmith, Andrea J

AU - Eldar, Yonina C

N1 - Funding Information: ∗This work was supported in part by the US - Israel Binational Science Foundation under grant No. 2026094, by the Israel Science Foundation under grant No. 0100101, by the Office of the Naval Research under grant No. 18-1-2191, and by the Discovery Grant from the Natural Sciences and Engineering Research Council of Canada (NSERC) and Canada Foundation for Innovation (CFI), John R. Evans Leader Fund. Publisher Copyright: © 2021 IEEE.

PY - 2021/7/11

Y1 - 2021/7/11

N2 - We present a data-driven framework to symbol detection design that combines machine learning (ML) and model-based algorithms. The resulting data-driven receivers are most suitable for systems where the underlying channel models are poorly understood, highly complex, or do not well-capture the underlying physics. Our approach is unique in that it only replaces the channel-model-based computations with dedicated neural networks that can be trained from a small amount of data, while keeping the general algorithm intact. Our results demonstrate that these techniques can yield performance close to that of model-based algorithms with perfect model knowledge without knowing the exact channel model or state.

AB - We present a data-driven framework to symbol detection design that combines machine learning (ML) and model-based algorithms. The resulting data-driven receivers are most suitable for systems where the underlying channel models are poorly understood, highly complex, or do not well-capture the underlying physics. Our approach is unique in that it only replaces the channel-model-based computations with dedicated neural networks that can be trained from a small amount of data, while keeping the general algorithm intact. Our results demonstrate that these techniques can yield performance close to that of model-based algorithms with perfect model knowledge without knowing the exact channel model or state.

UR - http://www.scopus.com/inward/record.url?scp=85113514994&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/SSP49050.2021.9513859

DO - https://doi.org/10.1109/SSP49050.2021.9513859

M3 - Paper

SP - 571

EP - 575

T2 - 21st IEEE Statistical Signal Processing Workshop, SSP 2021

Y2 - 11 July 2021 through 14 July 2021

ER -

Data-Driven Symbol Detection Via Model-Based Machine Learning

Abstract

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this