TR2021-110
Zero-Multiplier Sparse DNN Equalization for Fiber-Optic QAM Systems with Probabilistic Amplitude Shaping
-
- , "Zero-Multiplier Sparse DNN Equalization for Fiber-Optic QAM Systems with Probabilistic Amplitude Shaping", European Conference on Optical Communication (ECOC), DOI: 10.1109/ECOC52684.2021.9605870, September 2021.BibTeX TR2021-110 PDF Presentation
- @inproceedings{Koike-Akino2021sep,
- author = {Koike-Akino, Toshiaki and Wang, Ye and Kojima, Keisuke and Parsons, Kieran and Yoshida, Tsuyoshi},
- title = {Zero-Multiplier Sparse DNN Equalization for Fiber-Optic QAM Systems with Probabilistic Amplitude Shaping},
- booktitle = {European Conference on Optical Communication (ECOC)},
- year = 2021,
- month = sep,
- publisher = {IEEE},
- doi = {10.1109/ECOC52684.2021.9605870},
- isbn = {978-1-6654-3868-1},
- url = {https://www.merl.com/publications/TR2021-110}
- }
- , "Zero-Multiplier Sparse DNN Equalization for Fiber-Optic QAM Systems with Probabilistic Amplitude Shaping", European Conference on Optical Communication (ECOC), DOI: 10.1109/ECOC52684.2021.9605870, September 2021.
-
MERL Contacts:
-
Research Areas:
Abstract:
We propose a multiplier-less deep neural network (DNN) to mitigate fiber-nonlinear distortion of shaped constellations. Our DNN achieves an excellent performance-complexity trade-off with progressive lottery ticket hypothesis (LHT) weight pruning and additive powers-of-two (APoT) quantization.