O
Ognjen Jovanovic
Researcher at Technical University of Denmark
Publications - 15
Citations - 66
Ognjen Jovanovic is an academic researcher from Technical University of Denmark. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 2, co-authored 7 publications receiving 10 citations.
Papers
More filters
Journal ArticleDOI
Gradient-Free Training of Autoencoders for Non-Differentiable Communication Channels
TL;DR: In this article, a gradient-free training method based on the cubature Kalman filter was proposed for non-differential channel models and the autoencoder was employed to perform geometric constellation shaping on differentiable communication channels.
Proceedings ArticleDOI
End-to-end Learning of a Constellation Shape Robust to Variations in SNR and Laser Linewidth.
TL;DR: In this article, an autoencoder-based geometric shaping that learns a constellation robust to SNR and laser linewidth estimation errors is proposed, which maintains a shaping gain in mutual information (up to 0.3 bits/symbol).
Journal ArticleDOI
Gradient-free training of autoencoders for non-differentiable communication channels
TL;DR: In this article, a gradient-free training method based on the cubature Kalman filter was proposed for non-differential channel models and the autoencoder was employed to perform geometric constellation shaping on differentiable communication channels.
Posted Content
End-to-end Learning of a Constellation Shape Robust to Channel Condition Uncertainties
TL;DR: In this article, the authors proposed to geometrically optimize a constellation shape that is robust to uncertainties in the channel conditions by utilizing end-to-end learning, and the results indicate that the learned constellations are more robust to uncertainty in channel conditions compared to a standard constellation scheme such as quadrature amplitude modulation and more importantly standard geometric constellation shaping techniques.
Proceedings Article
Recent advances in constellation optimization for fiber-optic channels
TL;DR: In this paper , the autoencoder concept for geometric constellation shaping is discussed and applications in coherent optical fiber communications are compared, and the quantization problem of finite precision DAC and ADC is addressed.