Abstract
We use deep neural network (DNN) to compensate for Kerr-induced nonlinearity in fiber-optic communications. The proposed DNN is scalable to high-order modulations by employing multi-label classification, achieving greater than 1.2 dB gain in nonlinear regimes.
© 2018 The Author(s)
PDF ArticleMore Like This
Chang Wang, Guoyao Chen, Haoyang Wang, Lin Sun, Jiangbing Du, Zuyuan He, Ke Xu, and Bo Liu
Su4C.5 Asia Communications and Photonics Conference (ACP) 2018
Xinyu Liu, Yongjun Wang, and Chao Li
M4A.275 Asia Communications and Photonics Conference (ACP) 2020
C. P. Tsekrekos, C. Sánchez Costa, M. A. Z. Al-Khateeb, F. Wen, O. Sidelnikov, and S. Sygletos
STh1C.4 CLEO: Science and Innovations (CLEO:S&I) 2018