To circumvent the non-parallelizability of recurrent neural network-based equalizers, we propose knowledge distillation to recast the RNN into a parallelizable feedforward structure. The latter shows 38\% latency decrease, while impacting the Q-factor by only 0.5dB.
Cite
@article{arxiv.2212.04569,
title = {Knowledge Distillation Applied to Optical Channel Equalization: Solving the Parallelization Problem of Recurrent Connection},
author = {Sasipim Srivallapanondh and Pedro J. Freire and Bernhard Spinnler and Nelson Costa and Antonio Napoli and Sergei K. Turitsyn and Jaroslaw E. Prilepsky},
journal= {arXiv preprint arXiv:2212.04569},
year = {2022}
}
Comments
Paper Accepted for Oral presentation - OFC 2023 (Optical Fiber Communication Conference)