Artificial neural networks for photonic applications—from algorithms to implementation: tutorial
This tutorial–review on applications of artificial neural networks in photonics targets a broad
audience, ranging from optical research and engineering communities to computer science …
audience, ranging from optical research and engineering communities to computer science …
End-to-end learning for VCSEL-based optical interconnects: State-of-the-art, challenges, and opportunities
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 …
main workhorse within data centers, supercomputers, and even vehicles, providing low-cost …
End-to-end learning of joint geometric and probabilistic constellation shaping
We present a novel autoencoder-based learning of joint geometric and probabilistic
constellation shaping for coded-modulation systems. It can maximize either the mutual …
constellation shaping for coded-modulation systems. It can maximize either the mutual …
A multi-rate approach for nonlinear pre-distortion using end-to-end deep learning in IM-DD systems
Modern intra-data center (IDC) interconnects leverage robust and low-cost intensity
modulation (IM) and direct detection (DD) optical links, based on multimode fibers (MMFs) …
modulation (IM) and direct detection (DD) optical links, based on multimode fibers (MMFs) …
Memory-aware end-to-end learning of channel distortions in optical coherent communications
We implement a new variant of the end-to-end learning approach for the performance
improvement of an optical coherent-detection communication system. The proposed solution …
improvement of an optical coherent-detection communication system. The proposed solution …
Modulation format and digital signal processing for IM-DD optics at post-200G era
200-Gb/s per lane intensity-modulation (IM) direct-detection (DD) optics are being
commercialized to support 800G and 1.6 T applications inside datacenters. Though IM-DD …
commercialized to support 800G and 1.6 T applications inside datacenters. Though IM-DD …
Towards FPGA implementation of neural network-based nonlinearity mitigation equalizers in coherent optical transmission systems
PJ Freire, M Anderson, B Spinnler, T Bex… - 2022 European …, 2022 - ieeexplore.ieee.org
For the first time, recurrent and feedforward neural network-based equalizers for nonlinearity
compensation are implemented in an FPGA, with a level of complexity comparable to that of …
compensation are implemented in an FPGA, with a level of complexity comparable to that of …
Blind channel equalization using vector-quantized variational autoencoders
State-of-the-art high-spectral-efficiency communication systems employ high-order
modulation formats coupled with high symbol rates to accommodate the ever-growing …
modulation formats coupled with high symbol rates to accommodate the ever-growing …
Nonlinear pre-distortion through a multi-rate end-to-end learning approach over VCSEL-MMF IM-DD optical links
We experimentally demonstrate a nonlinear digital pre-distorter for PAM-M shaping in
VCSEL+ MMF IM-DD links able to operate at a generic baud rate using a fractional sample …
VCSEL+ MMF IM-DD links able to operate at a generic baud rate using a fractional sample …
Low-cost, large-coverage, and high-flexibility coherent PON for next-generation access networks: advances, challenges, and prospects
Increasing bandwidth requirements have posed significant challenges for traditional access
networks. It is difficult for intensity modulation/direct detection to meet the power budget and …
networks. It is difficult for intensity modulation/direct detection to meet the power budget and …