CNN Nonlinear Equalizer with Reducing the Dimensionality of Feature Maps

Shuo Liu; Yongjun Wang; Lu Han; Chao Li; Xingyuan Huang; Qi Zhang; Xiangjun Xin

doi:10.1109/ICOCN59242.2023.10236423

CNN Nonlinear Equalizer with Reducing the Dimensionality of Feature Maps

Shuo Liu^*, Yongjun Wang^*, Lu Han, Chao Li, Xingyuan Huang, Qi Zhang, Xiangjun Xin

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, we propose a method of feature map dimensionality reduction as the input of CNN. We validate the complexity advantages of this scheme in a 120Gb/s PDM 64QAM coherent optical communication system.

Original language	English
Title of host publication	2023 21st International Conference on Optical Communications and Networks, ICOCN 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350343502
DOIs	https://doi.org/10.1109/ICOCN59242.2023.10236423
Publication status	Published - 2023
Externally published	Yes
Event	21st International Conference on Optical Communications and Networks, ICOCN 2023 - Qufu, China Duration: 31 Jul 2023 → 3 Aug 2023

Publication series

Name	2023 21st International Conference on Optical Communications and Networks, ICOCN 2023

Conference

Conference	21st International Conference on Optical Communications and Networks, ICOCN 2023
Country/Territory	China
City	Qufu
Period	31/07/23 → 3/08/23

Keywords

Non-linear compensation
dimensionality reduction
perturbation theory

Access to Document

10.1109/ICOCN59242.2023.10236423

Cite this

Liu, S., Wang, Y., Han, L., Li, C., Huang, X., Zhang, Q., & Xin, X. (2023). CNN Nonlinear Equalizer with Reducing the Dimensionality of Feature Maps. In 2023 21st International Conference on Optical Communications and Networks, ICOCN 2023 (2023 21st International Conference on Optical Communications and Networks, ICOCN 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICOCN59242.2023.10236423

@inproceedings{545fd8fe075b40308d5559fa60a6e91e,

title = "CNN Nonlinear Equalizer with Reducing the Dimensionality of Feature Maps",

abstract = "In this paper, we propose a method of feature map dimensionality reduction as the input of CNN. We validate the complexity advantages of this scheme in a 120Gb/s PDM 64QAM coherent optical communication system.",

keywords = "Non-linear compensation, dimensionality reduction, perturbation theory",

author = "Shuo Liu and Yongjun Wang and Lu Han and Chao Li and Xingyuan Huang and Qi Zhang and Xiangjun Xin",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 21st International Conference on Optical Communications and Networks, ICOCN 2023 ; Conference date: 31-07-2023 Through 03-08-2023",

year = "2023",

doi = "10.1109/ICOCN59242.2023.10236423",

language = "English",

series = "2023 21st International Conference on Optical Communications and Networks, ICOCN 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 21st International Conference on Optical Communications and Networks, ICOCN 2023",

address = "United States",

}

Liu, S, Wang, Y, Han, L, Li, C, Huang, X, Zhang, Q & Xin, X 2023, CNN Nonlinear Equalizer with Reducing the Dimensionality of Feature Maps. in 2023 21st International Conference on Optical Communications and Networks, ICOCN 2023. 2023 21st International Conference on Optical Communications and Networks, ICOCN 2023, Institute of Electrical and Electronics Engineers Inc., 21st International Conference on Optical Communications and Networks, ICOCN 2023, Qufu, China, 31/07/23. https://doi.org/10.1109/ICOCN59242.2023.10236423

CNN Nonlinear Equalizer with Reducing the Dimensionality of Feature Maps. / Liu, Shuo; Wang, Yongjun; Han, Lu et al.
2023 21st International Conference on Optical Communications and Networks, ICOCN 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 21st International Conference on Optical Communications and Networks, ICOCN 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - CNN Nonlinear Equalizer with Reducing the Dimensionality of Feature Maps

AU - Liu, Shuo

AU - Wang, Yongjun

AU - Han, Lu

AU - Li, Chao

AU - Huang, Xingyuan

AU - Zhang, Qi

AU - Xin, Xiangjun

PY - 2023

Y1 - 2023

N2 - In this paper, we propose a method of feature map dimensionality reduction as the input of CNN. We validate the complexity advantages of this scheme in a 120Gb/s PDM 64QAM coherent optical communication system.

AB - In this paper, we propose a method of feature map dimensionality reduction as the input of CNN. We validate the complexity advantages of this scheme in a 120Gb/s PDM 64QAM coherent optical communication system.

KW - Non-linear compensation

KW - dimensionality reduction

KW - perturbation theory

UR - http://www.scopus.com/inward/record.url?scp=85173124606&partnerID=8YFLogxK

U2 - 10.1109/ICOCN59242.2023.10236423

DO - 10.1109/ICOCN59242.2023.10236423

M3 - Conference contribution

AN - SCOPUS:85173124606

T3 - 2023 21st International Conference on Optical Communications and Networks, ICOCN 2023

BT - 2023 21st International Conference on Optical Communications and Networks, ICOCN 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 21st International Conference on Optical Communications and Networks, ICOCN 2023

Y2 - 31 July 2023 through 3 August 2023

ER -

Liu S, Wang Y, Han L, Li C, Huang X, Zhang Q et al. CNN Nonlinear Equalizer with Reducing the Dimensionality of Feature Maps. In 2023 21st International Conference on Optical Communications and Networks, ICOCN 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 21st International Conference on Optical Communications and Networks, ICOCN 2023). doi: 10.1109/ICOCN59242.2023.10236423

CNN Nonlinear Equalizer with Reducing the Dimensionality of Feature Maps

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this