… coding scheme with both encoder and decoder powered by neural networks … -art channel
codes under AWGN channels for a moderate block length. We demonstrate that channel coding…

… towards practical codeword lengths, we revisit the idea of Turbo-autoencoders for …
Turbo-autoencoders from the literature and compare the concept with state-of-the-art classical …

… code from solely gradient descent: Turbo Autoencoder (TurboAE) [18], which is the first neural
code with block length coding … Most channel coding research aims at designing code for …

… More explicitly, first of all, we design the MC-AE independently of both the channel coding
arrangement and of the channel model, where the output layer of the MC-AE decoder is …

… turbo codes as an implicit regularization, ie, using a concatenation of a turbo code and an
autoencoder. … a perfectly trained autoencoder can provide the optimum channel code even for …

… Abstract—Channel coding and modulation are two … channel coding and the modulation
blocks are modeled as neural networks. Our proposed architecture combines Turbo Autoencoder …

… deep learning-based channel codes that integrate an attention mechanism into turbo code
autoencoders, referred to as ATT-TurboAE, to enhance channel coding and reconstruction …

… channels; moreover, TurboAE outperforms the state-of-theart codes under non-canonical
settings in terms of reliability. TurboAE shows that the development of channel coding design …

… -TI outperforms TURBOAE and LTE Turbo codes for several channels of interest. We also …
—neural channel coding, Turbo autoencoder, deep learning, CNN, fading channels, chirp …

… autoencoder-based channel coding scheme in the presence of inter-symbol interference (ISI)
and additive white Gaussian noise (AWGN), supporting arbitrary coding … turbo autoencoder …