Estimating and Optimizing of Deep Relay Networks

Ido Binyamini, Itsik Bergel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Recent works showed that operating amplify-andforward relays in their nonlinear regimes can bring huge performance gains. However, the training of such a nonlinear network requires a knowledge of the channel gains. This work proposes a novel triplet network approach, where we copy the actual network into both an estimation twin and an optimization twin. The channel estimation is based on the transmission of data from a transmitter while taking measurements only at the network output. We show that this novel approach succeeds in estimating channel gains even in deep relay networks where measurements are taken through 12 layers of relays.

Original languageEnglish
Title of host publicationSPAWC 2025 - 2025 IEEE 26th International Workshop on Signal Processing and Artificial Intelligence for Wireless Communications - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665477765
DOIs
StatePublished - 2025
Event26th IEEE International Workshop on Signal Processing and Artificial Intelligence for Wireless Communications, SPAWC 2025 - Surrey, United Kingdom
Duration: 7 Jul 202510 Jul 2025

Publication series

NameIEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC
ISSN (Print)2325-3789

Conference

Conference26th IEEE International Workshop on Signal Processing and Artificial Intelligence for Wireless Communications, SPAWC 2025
Country/TerritoryUnited Kingdom
CitySurrey
Period7/07/2510/07/25

Bibliographical note

Publisher Copyright:
© 2025 IEEE.

Fingerprint

Dive into the research topics of 'Estimating and Optimizing of Deep Relay Networks'. Together they form a unique fingerprint.

Cite this