List Autoencoder: Towards Deep Learning Based Reliable Transmission Over Noisy Channels
This work addresses the problem of improving error correction in communication systems for applications requiring high reliability, but it is incremental as it builds on existing autoencoder and list decoding concepts.
The paper tackles reliable data transmission over noisy channels by introducing a list autoencoder (listAE) that outputs multiple decoded message candidates, and shows that their proposed incremental-redundancy AE under CRC-aided list decoding achieves meaningful coding gain over Turbo-AE and polar codes at low block error rates.
In this paper, we present list autoencoder (listAE) to mimic list decoding used in classical coding theory. With listAE, the decoder network outputs a list of decoded message word candidates. To train the listAE, a genie is assumed to be available at the output of the decoder. A specific loss function is proposed to optimize the performance of a genie-aided (GA) list decoding. The listAE is a general framework and can be used with any AE architecture. We propose a specific architecture, referred to as incremental-redundancy AE (IR-AE), which decodes the received word on a sequence of component codes with non-increasing rates. Then, the listAE is trained and evaluated with both IR-AE and Turbo-AE. Finally, we employ cyclic redundancy check (CRC) codes to replace the genie at the decoder output and obtain a CRC aided (CA) list decoder. Our simulation results show that the IR-AE under CA list decoding demonstrates meaningful coding gain over Turbo-AE and polar code at low block error rates range.