@inproceedings{ad323589a8c7499da6381268916ee7d0,
title = "Unsupervised-Learning Neural Network for Fiber Nonlinearity Compensation",
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.",
keywords = "Fiber nonlinearity compensation, coherent optical fiber communication, neural network",
author = "Pinjing He and Feilong Wu and Meng Yang and Aiying Yang and Peng Guo and Yaojun Qiao and Xiangjun Xin",
note = "Publisher Copyright: {\textcopyright} 2022 SPIE.; 2021 International Conference on Optical Instruments and Technology: Optical Communication and Optical Signal Processing ; Conference date: 08-04-2022 Through 10-04-2022",
year = "2022",
doi = "10.1117/12.2616544",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Jian Chen and Yi Dong and Shilong Pan and Yang Qiu and Fabien Bretenaker",
booktitle = "2021 International Conference on Optical Instruments and Technology",
address = "United States",
}