47 citations · 129 across the 15 of their papers we have counts for
15 papers
BICM-compatible Rate Adaptive Geometric Constellation Shaping Using Optimized Many-to-one Labeling
Metodi Plamenov Yankov, Smaranika Swain, Ognjen Jovanovic +2
In this paper, a rate adaptive geometric constellation shaping (GCS) scheme which is fully backward-compatible with existing state of the art bit-interleaved coded modulation (BICM…
Differentiable Machine Learning-Based Modeling for Directly-Modulated Lasers
Sergio Hernandez, Ognjen Jovanovic, Christophe Peucheret +2
End-to-end learning has become a popular method for joint transmitter and receiver optimization in optical communication systems. Such approach may require a differentiable channel…
Low-complexity Samples versus Symbols-based Neural Network Receiver for Channel Equalization
Yevhenii Osadchuk, Ognjen Jovanovic, Stenio M. Ranzini +4
Low-complexity neural networks (NNs) have successfully been applied for digital signal processing (DSP) in short-reach intensity-modulated directly detected optical links, where ch…
Addressing Data Scarcity in Optical Matrix Multiplier Modeling Using Transfer Learning
Ali Cem, Ognjen Jovanovic, Siqi Yan +3
We present and experimentally evaluate using transfer learning to address experimental data scarcity when training neural network (NN) models for Mach-Zehnder interferometer mesh-b…
Rate Adaptive Geometric Constellation Shaping Using Autoencoders and Many-To-One Mapping
Metodi P. Yankov, Ognjen Jovanovic, Darko Zibar +1
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. An aut…
Data-Driven Modeling of Directly-Modulated Lasers
Sergio Hernandez Fernandez, Christophe Peucheret, Ognjen Jovanovic +2
The end-to-end optimization of links based on directly-modulated lasers may require an analytically differentiable channel. We overcome this problem by developing and comparing dif…
Multi-Wavelength Transponders for High-capacity Optical Networks: A Physical-layer-aware Network Planning Study
Jasper Müller, Ognjen Jovanovic, Tobias Fehenberger +3
Continued cost- and power-efficient capacity scaling in optical networks is imperative to keep pace with ever-increasing traffic demands. In this paper, we investigate multi-wavele…
Comparison of Single-Wavelength and Multi-Wavelength Transponders in a Physical-layer-aware Network Planning Study
Jasper Müller, Ognjen Jovanovic, Carmen Mas-Machuca +3
Based on suitable system architectures and realistic specifications, transmit OSNR penalties and spectral constraints of multi-wavelength transponders are identified and analyzed i…
Rate Adaptive Autoencoder-based Geometric Constellation Shaping
Ognjen Jovanovic, Metodi P. Yankov, Francesco Da Ros +1
An autoencoder is used to optimize bit-to-symbol mappings for geometric constellation shaping. The mappings allow for net rate adaptivity without additional hardware complexity, wh…
Reservoir Computing-based Multi-Symbol Equalization for PAM 4 Short-reach Transmission
Yevhenii Osadchuk, Ognjen Jovanovic, Darko Zibar +1
We propose spectrum-sliced reservoir computer-based (RC) multi-symbol equalization for 32-GBd PAM4 transmission. RC with 17 symbols at the output achieves an order of magnitude red…
Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning
Ali Cem, Ognjen Jovanovic, Siqi Yan +3
We demonstrate transfer learning-assisted neural network models for optical matrix multipliers with scarce measurement data. Our approach uses <10\% of experimental data needed for…
Geometric Constellation Shaping for Fiber-Optic Channels via End-to-End Learning
Ognjen Jovanovic, Francesco Da Ros, Darko Zibar +1
End-to-end learning has become a popular method to optimize a constellation shape of a communication system. When the channel model is differentiable, end-to-end learning can be ap…
End-to-end Learning of a Constellation Shape Robust to Channel Condition Uncertainties
Ognjen Jovanovic, Metodi P. Yankov, Francesco Da Ros +1
Vendor interoperability is one of the desired future characteristics of optical networks. This means that the transmission system needs to support a variety of hardware with differ…
End-to-end Learning of a Constellation Shape Robust to Variations in SNR and Laser Linewidth
Ognjen Jovanovic, Metodi P. Yankov, Francesco Da Ros +1
We propose an autoencoder-based geometric shaping that learns a constellation robust to SNR and laser linewidth estimation errors. This constellation maintains shaping gain in mutu…
Gradient-free training of autoencoders for non-differentiable communication channels
Ognjen Jovanovic, Metodi Plamenov Yankov, Francesco Da Ros +1
Training of autoencoders using the back-propagation algorithm is challenging for non-differential channel models or in an experimental environment where gradients cannot be compute…