TY - JOUR
T1 - End-to-End Learning for VCSEL-based Optical Interconnects
T2 - State-of-the-Art, Challenges, and Opportunities
AU - Srinivasan, Muralikrishnan
AU - Song, Jinxiang
AU - Grabowski, Alexander
AU - Szczerba, Krzysztof
AU - Iversen, Holger K.
AU - Schmidt, Mikkel N.
AU - Zibar, Darko
AU - Schröder, Jochen
AU - Larsson, Anders
AU - Häger, Christian
AU - Wymeersch, Henk
PY - 2023
Y1 - 2023
N2 - Optical interconnects (OIs) based on vertical-cavity surface-emitting lasers (VCSELs) are the main workhorse within data centers, supercomputers, and even vehicles, providing low-cost, high-rate connectivity. VCSELs must operate under extremely harsh and time-varying conditions, thus requiring adaptive and flexible designs of the communication chain. Such designs can be built based on mathematical models (model-based design) or learned from data (machine learning (ML) based design). Various ML techniques have recently come to the forefront, replacing individual components in the transmitters and receivers with deep neural networks. Beyond such component-wise learning, end-to-end (E2E) autoencoder approaches can reach the ultimate performance through co-optimizing entire parameterized transmitters and receivers. This tutorial paper aims to provide an overview of ML for VCSEL-based OIs, with a focus on E2E approaches, dealing specifically with the unique challenges facing VCSELs, such as the wide temperature variations and complex models.
AB - Optical interconnects (OIs) based on vertical-cavity surface-emitting lasers (VCSELs) are the main workhorse within data centers, supercomputers, and even vehicles, providing low-cost, high-rate connectivity. VCSELs must operate under extremely harsh and time-varying conditions, thus requiring adaptive and flexible designs of the communication chain. Such designs can be built based on mathematical models (model-based design) or learned from data (machine learning (ML) based design). Various ML techniques have recently come to the forefront, replacing individual components in the transmitters and receivers with deep neural networks. Beyond such component-wise learning, end-to-end (E2E) autoencoder approaches can reach the ultimate performance through co-optimizing entire parameterized transmitters and receivers. This tutorial paper aims to provide an overview of ML for VCSEL-based OIs, with a focus on E2E approaches, dealing specifically with the unique challenges facing VCSELs, such as the wide temperature variations and complex models.
KW - Machine learning
KW - Optical communication
KW - VCSEL-based optical interconnects
KW - End-to-end learning
U2 - 10.1109/JLT.2023.3251660
DO - 10.1109/JLT.2023.3251660
M3 - Journal article
SN - 1558-2213
VL - 41
SP - 3261
EP - 3277
JO - Journal of Lightwave Technology
JF - Journal of Lightwave Technology
IS - 11
ER -