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

Neuromorphic computing implementing spiking neural networks (SNN) is a promising technology for reducing the footprint of optical transceivers, as required by the fast-paced growth of data center traffic. In this work, an SNN nonlinear demapper is designed and evaluated on a simulated intensity-modu...

Full description

Saved in:
Bibliographic Details
Published in:Journal of lightwave technology 2023-06, Vol.41 (11), p.1-8
Main Authors: Arnold, Elias, Bocherer, Georg, Strasser, Florian, Muller, Eric, Spilger, Philipp, Billaudelle, Sebastian, Weis, Johannes, Schemmel, Johannes, Calabro, Stefano, Kuschnerov, Maxim
Format: Article
Language:English
Subjects:
Adaptive optics
Artificial neural networks
Bit error rate
Data Centers
Equalization
Equalizers
Error correction
Hardware
Intensity-Modulation Direct-Detection
Neural networks
Neuromorphic computing
Neurons
Nonlinear optics
Optical Communication
Optical fiber dispersion
Software
Spiking
Spiking Neural Network
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neuromorphic computing implementing spiking neural networks (SNN) is a promising technology for reducing the footprint of optical transceivers, as required by the fast-paced growth of data center traffic. In this work, an SNN nonlinear demapper is designed and evaluated on a simulated intensity-modulation direct-detection link with chromatic dispersion. The SNN demapper is implemented in software and on the analog neuromorphic hardware system BrainScaleS-2 (BSS-2). For comparison, linear equalization (LE), Volterra nonlinear equalization (VNLE), and nonlinear demapping by an artificial neural network (ANN) implemented in software are considered. At a pre-forward error correction bit error rate of exponent-product2e-3, the software SNN outperforms LE by 1.5 dB, VNLE by 0.3 dB and the ANN by 0.5 dB. The hardware penalty of the SNN on BSS-2 is only 0.2 dB, i.e., also on hardware, the SNN performs better than all software implementations of the reference approaches. Hence, this work demonstrates that SNN demappers implemented on electrical analog hardware can realize powerful and accurate signal processing fulfilling the strict requirements of optical communications.
ISSN:0733-8724
1558-2213
DOI:10.1109/JLT.2023.3252819