Spiking neural network equalization for IM/DD optical communication

A spiking neural network (SNN) equalizer model suitable for electronic neuromorphic hardware is designed for an IM/DD link. The SNN achieves the same bit-error-rate as an artificial neural network, outperforming linear equalization.

Saved in:

Bibliographic Details
Main Authors:	Arnold, Elias (Author) , Böcherer, Georg (Author) , Müller, Eric (Author) , Spilger, Philipp (Author) , Schemmel, Johannes (Author) , Calabrò, Stefano (Author) , Kuschnerov, Maxim (Author)
Format:	Article (Journal) Chapter/Article
Language:	English
Published:	1 Jun 2022
Edition:	Version v2
In:	Arxiv Year: 2022, Pages: 1-5
DOI:	10.48550/arXiv.2205.04263
Online Access:	Verlag, lizenzpflichtig, Volltext: https://doi.org/10.48550/arXiv.2205.04263 Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/2205.04263
Author Notes:	Elias Arnold, Georg Böcherer, Eric Müller, Philipp Spilger, Johannes Schemmel, Stefano Calabrò, Maxim Kuschnerov

Description
Summary:	A spiking neural network (SNN) equalizer model suitable for electronic neuromorphic hardware is designed for an IM/DD link. The SNN achieves the same bit-error-rate as an artificial neural network, outperforming linear equalization.
Item Description:	Version 1 vom 9 Mai 2022, Version 2 vom 1 Juni 2022 Gesehen am 17.10.2022
Physical Description:	Online Resource
DOI:	10.48550/arXiv.2205.04263