Unsupervised-learning neural network for fiber nonlinearity compensation

Pinjing He; Feilong Wu; Meng Yang; Aiying Yang; Peng Guo; Yaojun Qiao; Xiangjun Xin

doi:10.1117/12.2616544

26 July 2022 Unsupervised-learning neural network for fiber nonlinearity compensation

Pinjing He, Feilong Wu, Meng Yang, Aiying Yang, Peng Guo, Yaojun Qiao, Xiangjun Xin

Proceedings Volume 12278, 2021 International Conference on Optical Instruments and Technology: Optical Communication and Optical Signal Processing; 122780I (2022) https://doi.org/10.1117/12.2616544
Event: 2021 International Conference on Optical Instruments and Technology, 2022, Online Only

Abstract

A ﬁber nonlinearity compensation scheme based on an unsupervised-learning neural network is proposed. In the proposed scheme, labels in the training data and weights of the neural network are iteratively updated until converging. To validate the proposed scheme, a 3200 km dual-polarization 16-QAM simulation link and an 1800 km single-polarization experimental link were carried out. Simulation and experiment results validate that the proposed method can achieve the same equalization performance as the supervised-learning-neural-network-based scheme, without any pre-deﬁned training data.

Citation Download Citation

Pinjing He, Feilong Wu, Meng Yang, Aiying Yang, Peng Guo, Yaojun Qiao, and Xiangjun Xin "Unsupervised-learning neural network for fiber nonlinearity compensation", Proc. SPIE 12278, 2021 International Conference on Optical Instruments and Technology: Optical Communication and Optical Signal Processing, 122780I (26 July 2022); https://doi.org/10.1117/12.2616544

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available