English

Knowledge Distillation Applied to Optical Channel Equalization: Solving the Parallelization Problem of Recurrent Connection

Signal Processing 2022-12-12 v1 Machine Learning

Abstract

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)

R2 v1 2026-06-28T07:26:53.321Z