Abstract
In this Letter, we propose and experimentally demonstrate a novel, to the best of our knowledge, sparse deep neural network-based nonlinear equalizer (SDNN-NLE). By identifying only the significant weight coefficients, our approach remarkably reduces the computational complexity, while still upholding the desired transmission accuracy. The insignificant weights are pruned in two phases: identifying the significance of each weight by pre-training the fully connected DNN-NLE with an adaptive L2-regularization and then pruning those insignificant ones away with a pre-defined sparsity. An experimental demonstration is conducted on a 112 Gbps PAM4 link over 40 km standard single-mode fiber with a 25 GHz externally modulated laser in O-band. Our experimental results illustrate that, for the 112 Gbps PAM4 signal at a received optical power of ${-}{5}\;{\rm dBm}$ over 40 km, the proposed SDNN-NLE exhibits promising solutions to effectively mitigate nonlinear distortions and outperforms a conventional fully connected Volterra equalizer (VE), conventional fully connected DNN-NLE, and sparse VE by providing 71%, 63%, and 41% complexity reduction, respectively, without degrading the system performance.
© 2021 Optical Society of America
Full Article | PDF ArticleMore Like This
Govind sharan Yadav, Chun-Yen Chuang, Kai-Ming Feng, Jhih-Heng Yan, Jyehong Chen, and Young-Kai Chen
Opt. Express 28(26) 38539-38552 (2020)
Junwei Zhang, Zhenrui Lin, Xiong Wu, Jie Liu, Alan Pak Tao Lau, Changjian Guo, Chao Lu, and Siyuan Yu
Opt. Express 29(14) 21891-21901 (2021)
Mingzhu Yin, Dongdong Zou, Wei Wang, Fan Li, and Zhaohui Li
Opt. Lett. 46(22) 5615-5618 (2021)