activity
20182021
most citedEnabling FDD Massive MIMO through Deep Learning-based Channel Prediction

45 citations · 54 across the 2 of their papers we have counts for

collaborators

6 papers

cs.IT2021

Serial vs. Parallel Turbo-Autoencoders and Accelerated Training for Learned Channel Codes

Jannis Clausius, Sebastian Dörner, Sebastian Cammerer +1

Attracted by its scalability towards practical codeword lengths, we revisit the idea of Turbo-autoencoders for end-to-end learning of PHY-Layer communications. For this, we study t…

cs.IT2021

Wiener Filter versus Recurrent Neural Network-based 2D-Channel Estimation for V2X Communications

Moritz Benedikt Fischer, Sebastian Dörner, Sebastian Cammerer +4

We compare the potential of neural network (NN)-based channel estimation with classical linear minimum mean square error (LMMSE)-based estimators, also known as Wiener filtering. F…

cs.IT20209 cited

Deep-learning Autoencoder for Coherent and Nonlinear Optical Communication

Tim Uhlemann, Sebastian Cammerer, Alexander Span +2

Motivated by the recent success of end-to-end training of communications in the wireless domain, we strive to adapt the end-to-end-learning idea from the wireless case (i.e., linea…

cs.IT2019

On Recurrent Neural Networks for Sequence-based Processing in Communications

Daniel Tandler, Sebastian Dörner, Sebastian Cammerer +1

In this work, we analyze the capabilities and practical limitations of neural networks (NNs) for sequence-based signal processing which can be seen as an omnipresent property in al…

cs.IT201945 cited

Enabling FDD Massive MIMO through Deep Learning-based Channel Prediction

Maximilian Arnold, Sebastian Dörner, Sebastian Cammerer +3

A major obstacle for widespread deployment of frequency division duplex (FDD)-based Massive multiple-input multiple-output (MIMO) communications is the large signaling overhead for…

cs.IT2018

Online Label Recovery for Deep Learning-based Communication through Error Correcting Codes

Stefan Schibisch, Sebastian Cammerer, Sebastian Dörner +2

We demonstrate that error correcting codes (ECCs) can be used to construct a labeled data set for finetuning of "trainable" communication systems without sacrificing resources for…