Back to Search
Start Over
Few-bit Quantization of Neural Networks for Nonlinearity Mitigation in a Fiber Transmission Experiment
- Publication Year :
- 2022
-
Abstract
- A neural network is quantized for the mitigation of nonlinear and components distortions in a 16-QAM 9x50km dual-polarization fiber transmission experiment. Post-training additive power-of-two quantization at 6 bits incurs a negligible Q-factor penalty. At 5 bits, the model size is reduced by 85%, with 0.8 dB penalty.<br />Comment: 4 pages ,3 figuers
- Subjects :
- Electrical Engineering and Systems Science - Signal Processing
Subjects
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2205.11284
- Document Type :
- Working Paper