English

Spiking Neural Network Equalization on Neuromorphic Hardware for IM/DD Optical Communication

Signal Processing 2022-06-02 v1

Abstract

A spiking neural network (SNN) non-linear equalizer model is implemented on the mixed-signal neuromorphic hardware system BrainScaleS-2 and evaluated for an IM/DD link. The BER 2e-3 is achieved with a hardware penalty less than 1 dB, outperforming numeric linear equalization.

Keywords

Cite

@article{arxiv.2206.00401,
  title  = {Spiking Neural Network Equalization on Neuromorphic Hardware for IM/DD Optical Communication},
  author = {Elias Arnold and Georg Böcherer and Eric Müller and Philipp Spilger and Johannes Schemmel and Stefano Calabrò and Maxim Kuschnerov},
  journal= {arXiv preprint arXiv:2206.00401},
  year   = {2022}
}
R2 v1 2026-06-24T11:35:48.408Z