Experimental Study of Deep Neural Network Equalizers Performance in Optical Links

We propose a convolutional-recurrent channel equalizer and experimentally demonstrate 1dB Q-factor improvement both in single-channel and 96×WDM, DP-16QAM transmission over 450km of TWC fiber. The new equalizer outperforms previous NN-based approaches and a 3-steps-per-span DBP.

Engineering Physics Computer Science

View graph Source

Paper

References (10)

01Complex-Valued Neural Network Design for Mitigation of Signal Distortions in Optical LinksPedro J. Freire, Vladislav Neskornuik, A. Napoli et al.2020 · Journal of Lightwave Technology · 59 citations

02Physics-Based Deep Learning for Fiber-Optic Communication SystemsChristian Häger, H. Pfister2020 · IEEE Journal on Selected Areas in Communications · 90 citations In Library

03Speech enhancement using progressive learning-based convolutional recurrent neural networkAndong Li, Minmin Yuan, C. Zheng et al.2020 · 72 citations

04Compensation of Fiber Nonlinearities in Digital Coherent Systems Leveraging Long Short-Term Memory Neural NetworksS. Deligiannidis, A. Bogris, C. Mesaritakis et al.2020 · Journal of Lightwave Technology · 84 citations In Library

05Field and lab experimental demonstration of nonlinear impairment compensation using neural networksShaoliang Zhang, F. Yaman, Kohei Nakamura et al.2019 · Nature Communications · 157 citations

06Equalization performance and complexity analysis of dynamic deep neural networks in long haul transmission systems.O. Sidelnikov, A. Redyuk, S. Sygletos2018 · Optics Express · 76 citations

07Applying Neural Networks in Optical Communication Systems: Possible PitfallsT. A. Eriksson, H. Bülow, A. Leven2017 · IEEE Photonics Technology Letters · 144 citations In Library

08Convolutional recurrent neural networks for music classificationKeunwoo Choi, György Fazekas, Mark B. Sandler et al.2016 · IEEE International Conference on Acoustics, Speech, and Signal Processing · 537 citations In Library

09Adaptive digital back-propagation for optical communication systemsChien-Yu Lin, A. Napoli, B. Spinnler et al.2014 · Optical Fiber Communications Conference and Exhibition · 35 citations

10Data-Aided Versus Blind Single-Carrier Coherent ReceiversM. Kuschnerov, M. Chouayakh, K. Piyawanno et al.2010 · IEEE Photonics Journal · 131 citations

Similar papers

High-efficient Equalizer based on the simplified Deep Neural Network for 56Gb/s/λ PAM-4 in C-band 10G DML-based Short reach systemYu Xi, Chenyu Wang, Xin Miao et al.2020 · Asia Communications and Photonics conference and Exhibition · 1 citation In Library

Nonlinear Equalizer by Feature Engineering Based-Deep Neural Network for Coherent Optical Communication SystemXinyu Liu, Yongjun Wang, Chao Li2020 · Asia Communications and Photonics conference and Exhibition · 5 citations In Library

Convolutional Neural Network Equalizer for Short-reach Optical Communication SystemsJing Zhang, Lianshan Yan, Lin Jiang et al.2020 · Asia Communications and Photonics conference and Exhibition · 4 citations In Library

A Deep Neural Network Equalizer for FSO Transmission SystemJyun-Wei Li, Song-Lin You, R. Shiu et al.2021 · Wireless and Optical Communications Conference · 3 citations In Library

Dynamic complex deep Neural Network Nonlinear Equalizer for 64 QAM Long-haul Transmission SystemsGovind Sharan Yadav, T. Tsuritani, S. Beppu et al.2019 · 2019 24th OptoElectronics and Communications Conference (OECC) and 2019 International Conference on Photonics in Switching and Computing (PSC) · 3 citations In Library

Multi-Task Learning Aided Neural Networks for Equalization in Coherent Optical SystemFangfang Huang, Xiatao Huang, J. Zhang et al.2022 · 2022 IEEE/CIC International Conference on Communications in China (ICCC) · 0 citations In Library

Performance versus Complexity Study of Neural Network Equalizers in Coherent Optical SystemsPedro J. Freire, Yevhenii Osadchuk, Bernhard Spinnler et al.2021 · Aston Publications Explorer (Aston University) In Library

Performance Versus Complexity Study of Neural Network Equalizers in Coherent Optical SystemsPedro J. Freire, Yevhenii Osadchuk, Bernhard Spinnler et al.2021 · Journal of Lightwave Technology In Library

Performance Versus Complexity Study of Neural Network Equalizers in Coherent Optical SystemsPedro J. Freire, Yevhenii Osadchuk, B. Spinnler et al.2021 · Journal of Lightwave Technology · 147 citations In Library

Machine-learning-based equalization for short-reach transmission: neural networks and reservoir computingFrancesco Da Ros, Stenio M. Ranzini, Roman Dischler et al.2021 · OPTO · 14 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal