Handling Multilayer Neural Network Nonlinear Equalizer Complexity and overfitting Challenges Using L1-Regularization for 112Gbps Optical Interconnects

Govind Sharan Yadav, Chun Yen Chuang, Kai Ming Feng*, Jyehong Chen, Young Kai Chen

*Corresponding author for this work

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

Abstract

We propose an L1-regularized multilayer neural network nonlinear equalizer (L1PML-NLE) for inter-data-center interconnects. Compared with conventional and sparse VNLE, the L1PML-NLE reduces 81% and 57.8% complexity with improved BER performance for 40-km 112-Gb/s PAM4 transmission.

Original languageEnglish
Title of host publicationOptoelectronics and Communications Conference, OECC 2021
PublisherThe Optical Society
ISBN (Electronic)9781557528209
StatePublished - 2021
Event2021 Opto-Electronics and Communications Conference, OECC 2021 - Hong Kong, Hong Kong
Duration: 3 Jul 20217 Jul 2021

Publication series

Name2021 Opto-Electronics and Communications Conference, OECC 2021

Conference

Conference2021 Opto-Electronics and Communications Conference, OECC 2021
Country/TerritoryHong Kong
CityHong Kong
Period3/07/217/07/21

Fingerprint

Dive into the research topics of 'Handling Multilayer Neural Network Nonlinear Equalizer Complexity and overfitting Challenges Using L1-Regularization for 112Gbps Optical Interconnects'. Together they form a unique fingerprint.

Cite this