Learning Robust Representations for Communications over Noisy Channels
This work addresses the problem of improving communication reliability over noisy channels for applications like wireless networks, but it is incremental as it builds on existing machine learning and information theory tools.
The paper tackled designing end-to-end communication systems using FCNNs without classical models, focusing on robust representations under power constraints, and found that iterative training with random noise power levels minimized block error rate for best error performance.
We explore the use of FCNNs (Fully Connected Neural Networks) for designing end-to-end communication systems without taking any inspiration from existing classical communications models or error control coding. This work relies solely on the tools of information theory and machine learning. We investigate the impact of using various cost functions based on mutual information and pairwise distances between codewords to generate robust representations for transmission under strict power constraints. Additionally, we introduce a novel encoder structure inspired by the Barlow Twins framework. Our results show that iterative training with randomly chosen noise power levels while minimizing block error rate provides the best error performance.