Deep learning has been recently applied to physical layer processing indigital communication systems . We introduce a novel deep learning solution for soft bitquantization across wideband channels . Our method is trained end-to-end withquantization- and entropy-aware augmentations to the loss function . When tested on channel distributions never seen during training, the proposed method achieves a compression gain of up to $10 \%$ inthe high SNR regime versus previous state-of-the-art methods . To encouragereproducible research, our implementation is publicly available athttps://://

Author(s) : Marius Arvinte, Jonathan I. Tamir

Links : PDF - Abstract

Code :

Keywords : deep - wideband - method - learning - aware -

Leave a Reply

Your email address will not be published. Required fields are marked *