论文信息 - Performance and Computational Complexity Evaluation for Neural Network-Based Short-Reach Optical Links

Performance and Computational Complexity Evaluation for Neural Network-Based Short-Reach Optical Links

The performance and computational complexity of neural network-based equalizers are experimentally evaluated for a 50-Gb/s 25-km PAM4 optical link. Equalizers with tanh activation function and 1 output help achieve better performance with moderate computational complexity.

Zhaopeng Xu | William Shieh | Jonathan H. Manton | Chuanbowen Sun

[1] Tao Gui,et al. Experimental study of PAM-4, CAP-16, and DMT for 100 Gb/s short reach optical transmission systems. , 2015, Optics express.

[2] Chuanbowen Sun,et al. Computational complexity comparison of feedforward/radial basis function/recurrent neural network-based equalizer for a 50-Gb/s PAM4 direct-detection optical link. , 2019, Optics express.