Abstract
The complex-valued fully connected neural networks are applied for nonlinearity compensation in fiber optic communication systems. The superiority of a such approach over the real-valued neural networks and linear compensation schemes is demonstrated.
© 2021 IEEE
PDF ArticleMore Like This
Zhiyuan Yang, Yiwen Wu, Hexun Jiang, Mengfan Fu, Lilin Yi, Weisheng Hu, and Qunbi Zhuge
T2B.3 Optoelectronics and Communications Conference (OECC) 2021
Chaoran Huang, Shinsuke Fujisawa, Thomas Ferreira de Lima, Alexander N. Tait, Eric Blow, Yue Tian, Simon Bilodeau, Aashu Jha, Fatih Yaman, Hussam G. Batshon, Hsuan-Tung Peng, Bhavin J. Shastri, Yoshihisa Inada, Ting Wang, and Paul. R. Prucnal
Th4C.6 Optical Fiber Communication Conference (OFC) 2020
Oleg Sidelnikov, Alexey Redyuk, Stylianos Sygletos, Mikhail Fedoruk, and Sergei Turitsyn
ci_p_6 The European Conference on Lasers and Electro-Optics (CLEO/Europe) 2021