Abstract
Low-complexity sparsely-connected multi-output neural networks are proposed for equalization in a 50-Gb/s 25-km PAM4 IM/DD system. Compared with traditional fully-connected single-output counterparts, a gross complexity reduction of 60.4%/56.7% can be achieved with 2-layer FNN/C-FNN architecture.
© 2022 The Author(s)
PDF Article | Presentation VideoMore Like This
Zhaopeng Xu, Chuanbowen Sun, Tonghui Ji, Shuangyu Dong, Xian Zhou, and William Shieh
S4I.1 Asia Communications and Photonics Conference (ACP) 2020
Chen Wang, Kaihui Wang, Yuxuan Tan, Junjie Ding, Bohan Sang, Feng Wang, Bowen Zhu, Miao Kong, Wen Zhou, and Jianjun Yu
Tu5.28 European Conference and Exhibition on Optical Communication (ECOC) 2022
Zhaopeng Xu, Shuangyu Dong, Chenxin Jiang, Jonathan H. Manton, and William Shieh
M5H.4 Asia Communications and Photonics Conference (ACP) 2021