Turbo Autoencoder with a Trainable Interleaver

TL;DR

This paper introduces TURBOAE-TI, a neural network-based coding scheme with a trainable interleaver, demonstrating improved performance over existing turbo codes across various practical noisy channels.

Contribution

It presents TURBOAE-TI, a novel neural architecture that jointly learns turbo coding and interleaver design for enhanced robustness in diverse channel conditions.

Findings

TURBOAE-TI outperforms TURBOAE and LTE Turbo codes on multiple channels.

The joint learning of interleaver and coding improves decoding reliability.

The proposed method provides interpretability insights into turbo coding mechanisms.

Abstract

A critical aspect of reliable communication involves the design of codes that allow transmissions to be robustly and computationally efficiently decoded under noisy conditions. Advances in the design of reliable codes have been driven by coding theory and have been sporadic. Recently, it is shown that channel codes that are comparable to modern codes can be learned solely via deep learning. In particular, Turbo Autoencoder (TURBOAE), introduced by Jiang et al., is shown to achieve the reliability of Turbo codes for Additive White Gaussian Noise channels. In this paper, we focus on applying the idea of TURBOAE to various practical channels, such as fading channels and chirp noise channels. We introduce TURBOAE-TI, a novel neural architecture that combines TURBOAE with a trainable 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 demonstrate that TURBOAE-TI outperforms TURBOAE and LTE Turbo codes for several channels of interest. We also provide interpretation analysis to better understand TURBOAE-TI.