Low-Complexity and Rapid-Adaptive Neural Network Equalizer Based on SkipNet for High-Speed Optical IM/DD Communication System
We propose and demonstrate a low-complexity and rapid-adaptive neural network equalizer based on SkipNet for high-speed optical IM/DD system, achieving 300- and 270-Gbps data transmission under B2B and 1-km fiber with improved sensitivity and data-rates.
Authors
- Zhixue He (ORCID: https://orcid.org/0000-0001-8533-2247)
- Junhao Zhao (ORCID: https://orcid.org/0000-0001-9896-5959)
- Zhongya Li (ORCID: https://orcid.org/0000-0003-1247-2059)
- An Yan (ORCID: https://orcid.org/0009-0009-2778-3803)
- Chengxi Wang (ORCID: https://orcid.org/0000-0002-3746-2159)
- Nan Chi (ORCID: https://orcid.org/0000-0003-4966-3844)
- Jianyang Shi (ORCID: https://orcid.org/0000-0002-5478-3704)
- Yingjun Zhou (ORCID: https://orcid.org/0000-0003-4177-4742)
- Junwen Zhang (ORCID: https://orcid.org/0000-0001-8041-1608)
Institutions
- National Engineering Research Center of Electromagnetic Radiation Control Materials (CN)
- Peng Cheng Laboratory (CN)
Publication Details
- Published
- 2025-06-29
- DOI
- https://doi.org/10.23919/oecc/psc62146.2025.11110563
- Primary Topic
- Optical Network Technologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00