Area-Efficient Neural Network CD Equalizer for 4×200Gb/s PAM4 CWDM4 Systems

Bo Liu, Christian Bluemm, Stefano Calabro, Bing Li, Ulf Schlichtmann

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

7 Scopus citations

Abstract

We use a neural network trained jointly by multi-task learning on datasets acquired at multiple wavelengths to mitigate the impact of chromatic dispersion in 4×200Gb/s CWDM4 PAM4 transmission. By sharing a single set of weights among all involved wavelengths, while keeping the biases reconfigurable, we enable logic simplification of multipliers in the VLSI implementation of the neural network. Results show that the neural network equalizer achieves a similar BER compared with a Volterra equalizer with 71% reduction in hardware area.

Original languageEnglish
Title of host publication2023 Optical Fiber Communications Conference and Exhibition, OFC 2023 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781957171180
DOIs
StatePublished - 2023
Event2023 Optical Fiber Communications Conference and Exhibition, OFC 2023 - San Diego, United States
Duration: 5 May 20239 May 2023

Publication series

Name2023 Optical Fiber Communications Conference and Exhibition, OFC 2023 - Proceedings

Conference

Conference2023 Optical Fiber Communications Conference and Exhibition, OFC 2023
Country/TerritoryUnited States
CitySan Diego
Period5/05/239/05/23

Fingerprint

Dive into the research topics of 'Area-Efficient Neural Network CD Equalizer for 4×200Gb/s PAM4 CWDM4 Systems'. Together they form a unique fingerprint.

Cite this