Abstract
A complex-valued triplet-input neural network for fiber nonlinearity compensation is proposed. Numerical results show 0.2 dB Q factor improvement and 25% computational complexity reduction, compared with the real-valued triplet-input neural network.
© 2021 The Author(s)
PDF ArticleMore Like This
Tao Xu, Xiatao Huang, Taowei Jin, Shaohua Hu, Jing Zhang, Bo Xu, Xingwen Yi, and Kun Qiu
JS2B.17 Optoelectronics and Communications Conference (OECC) 2021
O. S. Sunish Kumar, Lutz Lampe, Shenghang Luo, Mrinmoy Jana, Jeebak Mitra, and Chuandong Li
SpF2E.2 Signal Processing in Photonic Communications (SPPCom) 2021
Maximilian Schaedler, Fabio Pittalà, Stefano Calabrò, Georg Böcherer, Christian Bluemm, and Stephan Pachnicke
M5F.4 Optical Fiber Communication Conference (OFC) 2021