Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group
Conferences > OECC > 2021 > JS2B > JS2B.10

Overfitting in Four-Layer-DNN-Based Nonlinear Equalizer for Optical Communication Systems

Jinya Nakamura, Kai Ikuta, and Moriya Nakamura

Not Accessible

Your library or personal account may give you access

Abstract

We compared overfitting in four-layer-DNN- and three-layer-ANN-based nonlinear equalizers used for nonlinearity compensation in optical communication systems. The results showed that the DNN-based nonlinear equalizer had stronger overfitting characteristics for both PRBS and a random sequence.

© 2021 The Author(s)

PDF Article
More Like This
Nonlinear Equalizer by Feature Engineering Based-Deep Neural Network for Coherent Optical Communication System

Xinyu Liu, Yongjun Wang, and Chao Li
M4A.275 Asia Communications and Photonics Conference (ACP) 2020

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, and Young-Kai Chen
S3A.3 Optoelectronics and Communications Conference (OECC) 2021

Analysis of Neural Network Compensation for Fiber Nonlinearity in Coherent Optical Communication System Based on Perturbation Model

Tao Xu, Taowei Jin, Wenshan Jiang, Jing Zhang, Xingwen Yi, and Kun Qiu
T4A.37 Asia Communications and Photonics Conference (ACP) 2021

View More...
Select as filters
Select Topics Cancel
Top
       
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.
Privacy | Terms of Use