… We relate this issue mainly to the asymmetric interleaver in TurboAE. Hence, we propose
a novel interleaver design to flatten the curve. For the interleaver design, we note that each …

… interleaver design. We develop a carefully-designed training procedure and a novel
interleaver penalty function that are crucial in learning the interleaver and TURBOAE jointly. We …

… interleaver xπ = π(x) and de-interleaver x = π−1(xπ) shuffle and shuffle back the input sequence
x with the a pseudo random interleaving … of Turbo code and TurboAE, the interleaving is …

… One aims at learning a new code from solely gradient descent: Turbo Autoencoder (TurboAE)
[… Inspired by the blocklength gain produced by interleaving in TurboAE, we propose a new …

… Therefore, in search of suitable interleavers for TurboAE, it is important to examine the
interleavers designed for Turbo codes. In this paper, different interleavers are compared for …

… interleaver π (·) maps the ith entry of u to the jth entry of uπ with i = j ∀ i, j = 1, ..., k. Further,
a deinterleaver π−1 (·) is the inverse mapping of an interleaver. … The interleavers ensure that …

… decoder with interleaver, referred to as a Turbo Autoencoder (… -complete autoencoder with
interleaver and de-interleaver, … The architecture of a typical autoencoder consists of an input …

… autoencoder to be as good as possible and then fit the inner autoencoder to the resulting
outer autoencoder. … For all evaluations we use interleavers according to the LTE standard [16]. …

… Here, we present Autoturbo-DNA, a PyTorch framework for training error-correcting,
overcomplete autoencoders specifically tailored for the DNA data storage channel. It allows training …

… from interleaver design problem and for the sake of simplicity, in this paper a random interleaver
… There are existing works in the literature on interleaver desig of Turbo-AE which can be …