For the first time, multi-task learning is proposed to improve the flexibility of NN-based equalizers in coherent systems. A" single" NN-based equalizer improves Q-factor by up to 4 …
For the first time, multi-task learning is proposed to improve the flexibility of NN-based equalizers in coherent systems. A``single" NN-based equalizer improves Q-factor by up to 4 …
Z Xu, Q Wu, C Chen, H Ji, Y Yang… - 2023 IEEE 15th …, 2023 - ieeexplore.ieee.org
Intensity-modulated direct-detection (IMDD) systems dominate short-reach optical communication applications such as data center interconnects. However, the nonlinear …
Neural networks (NNs) have been successfully deployed in various fields. In NNs, a large number of multiply-accumulate (MAC) operations need to be performed. Most existing digital …
C Bluemm, B Liu, T Rahman, B Li… - … Opto-Electronics and …, 2023 - ieeexplore.ieee.org
Next generation DCI/DCN reaches 800Gb/s. Distances up to 10km make chromatic dispersion the bottleneck for O-band PAM4 CWDM4. Neural network equalizers provide …
B Liu, C Bluemm, S Calabro, B Li… - 49th European …, 2023 - ieeexplore.ieee.org
We compare hardware parallelization of CD equalizers on 10 km 4x200 Gb/s IM/DD PAM4 O-band measurements. A single neural network equalizer with multiple output symbols …