Learning Optimal PAM Levels for VCSEL-based Optical Interconnects
Paper in proceeding, 2022
An auto-encoder that optimizes a VCSEL-based fiber-optic system end-to-end and provides a 1.5dB sensitivity gain at higher temperatures is trained, utilizing a neural network that models the response of a VCSEL for a range of operating temperatures.
Author
Muralikrishnan Srinivasan
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Jinxiang Song
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Christian Häger
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Krzysztof Szczerba
Chalmers, Microtechnology and Nanoscience (MC2), Photonics
Henk Wymeersch
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Jochen Schröder
Chalmers, Microtechnology and Nanoscience (MC2), Photonics
2022 European Conference on Optical Communication, ECOC 2022
978-195717115-9 (ISBN)
European Conference on Optical Communication
Basel, Switzerland,
Basel, Switzerland,
Physics-Based Deep Learning for Optical Data Transmission and Distributed Sensing
Swedish Research Council (VR) (2020-04718), 2021-01-01 -- 2024-12-31.
Hot-Optics
Swedish Foundation for Strategic Research (SSF) (CHI19-0004), 2021-01-01 -- 2025-12-31.
Subject Categories
Telecommunications
Other Physics Topics
Communication Systems
ISBN
9781957171159