no code implementations • 10 Nov 2023 • Metodi Plamenov Yankov, Smaranika Swain, Ognjen Jovanovic, Darko Zibar, Francesco Da Ros
The GCS scheme is experimentally demonstrated in a multi-span recirculating loop coherent optical fiber transmission system with a total distance of up to 3000 km.
no code implementations • 27 Sep 2023 • Sergio Hernandez, Ognjen Jovanovic, Christophe Peucheret, Francesco Da Ros, Darko Zibar
End-to-end learning has become a popular method for joint transmitter and receiver optimization in optical communication systems.
no code implementations • 28 Aug 2023 • Yevhenii Osadchuk, Ognjen Jovanovic, Stenio M. Ranzini, Roman Dischler, Vahid Aref, Darko Zibar, Francesco Da Ros
In this work, we propose a low-complexity NN that performs samples-to-symbol equalization, meaning that the NN-based equalizer includes match filtering and downsampling.
no code implementations • 10 Aug 2023 • Ali Cem, Ognjen Jovanovic, Siqi Yan, Yunhong Ding, Darko Zibar, Francesco Da Ros
We present and experimentally evaluate using transfer learning to address experimental data scarcity when training neural network (NN) models for Mach-Zehnder interferometer mesh-based optical matrix multipliers.
no code implementations • 19 Jul 2023 • Metodi P. Yankov, Ognjen Jovanovic, Darko Zibar, Francesco Da Ros
A many-to-one mapping geometric constellation shaping scheme is proposed with a fixed modulation format, fixed FEC engine and rate adaptation with an arbitrarily small step.
no code implementations • 15 May 2023 • Sergio Hernandez Fernandez, Christophe Peucheret, Ognjen Jovanovic, Francesco Da Ros, Darko Zibar
The end-to-end optimization of links based on directly-modulated lasers may require an analytically differentiable channel.
no code implementations • 29 Nov 2022 • Yevhenii Osadchuk, Ognjen Jovanovic, Darko Zibar, Francesco Da Ros
We propose spectrum-sliced reservoir computer-based (RC) multi-symbol equalization for 32-GBd PAM4 transmission.
no code implementations • 29 Nov 2022 • Ali Cem, Ognjen Jovanovic, Siqi Yan, Yunhong Ding, Darko Zibar, Francesco Da Ros
We demonstrate transfer learning-assisted neural network models for optical matrix multipliers with scarce measurement data.
no code implementations • 16 Nov 2021 • Ognjen Jovanovic, Metodi P. Yankov, Francesco Da Ros, Darko Zibar
Two noise models are considered for the additive noise: white Gaussian noise and nonlinear interference noise model for fiber nonlinearities.
no code implementations • 1 Jun 2021 • Ognjen Jovanovic, Metodi P. Yankov, Francesco Da Ros, Darko Zibar
We propose an autoencoder-based geometric shaping that learns a constellation robust to SNR and laser linewidth estimation errors.
no code implementations • 21 Dec 2020 • Ognjen Jovanovic, Metodi Plamenov Yankov, Francesco Da Ros, Darko Zibar
Our results indicate that the autoencoder can be successfully optimized using the proposed training method to achieve better robustness to residual phase noise with respect to standard constellation schemes such as Quadrature Amplitude Modulation and Iterative Polar Modulation for the considered conditions.