Autoencoder-Based Error Correction Coding for One-Bit Quantization

TL;DR

This paper introduces a deep learning-based error correction coding scheme using autoencoders and turbo codes for one-bit quantized AWGN channels, achieving near-optimal performance and enabling higher-order modulation.

Contribution

It proposes a novel autoencoder-based error correction coding scheme combined with turbo codes, demonstrating improved performance for one-bit quantized channels and higher modulation schemes.

Findings

Nearly matches performance of perfectly trained autoencoder

Outperforms conventional turbo codes at finite block lengths

Enables operation with 16-QAM under one-bit quantization

Abstract

This paper proposes a novel deep learning-based error correction coding scheme for AWGN channels under the constraint of one-bit quantization in the receivers. Specifically, it is first shown that the optimum error correction code that minimizes the probability of bit error can be obtained by perfectly training a special autoencoder, in which "perfectly" refers to converging the global minima. However, perfect training is not possible in most cases. To approach the performance of a perfectly trained autoencoder with a suboptimum training, we propose utilizing turbo codes as an implicit regularization, i.e., using a concatenation of a turbo code and an autoencoder. It is empirically shown that this design gives nearly the same performance as to the hypothetically perfectly trained autoencoder, and we also provide a theoretical proof of why that is so. The proposed coding method is as bandwidth efficient as the integrated (outer) turbo code, since the autoencoder exploits the excess bandwidth from pulse shaping and packs signals more intelligently thanks to sparsity in neural networks. Our results show that the proposed coding scheme at finite block lengths outperforms conventional turbo codes even for QPSK modulation. Furthermore, the proposed coding method can make one-bit quantization operational even for 16-QAM.