ProductAE：基于神经乘积码的大信道码训练
ProductAE: Towards Training Larger Channel Codes based on Neural Product Codes
摘要：
近年来，通过深度学习自动化信道编码器和解码器的设计已经有了重大的研究活动。由于信道编码中的维度挑战，通过深度学习技术设计和训练相对较大的神经信道码非常复杂。因此，文献中的大多数结果限于具有小于100个信息比特的相对短的码。在本文中，我们构建了ProductAE，这是一个计算效率高的深度学习驱动（编码器，解码器）对系列，旨在以可管理的训练复杂度训练相对较大的信道码（编码器和解码器）。我们建立在经典乘积码的思想基础上，并提出使用较小的代码组件构建大型神经代码。更具体地说，我们提供了一个框架，该框架需要针对代码参数$(n_1,k_1)$和$(n_2,k_2)$训练神经编码器和解码器，使得$n_1 n_2=n$和$k_1 k_2=k$，而不是直接针对维度$k$和块长度$n$的大神经代码训练编码器和解码器。我们的训练结果表明，在所有信噪比（SNR）范围内，对于参数$(225,100)$的代码和参数$(441,196)$的中等长度代码，在连续消除（SC）解码器下，极化码有显著的增益。此外，我们的研究结果表明，有意义的增益超过涡轮自动编码器（TurboAE）和国家的最先进的经典代码。这是第一次设计乘积自编码器，也是训练大信道码的开创性工作。
英文摘要：
There have been significant research activities in recent years to automate the design of channel encoders and decoders via deep learning. Due the dimensionality challenge in channel coding, it is prohibitively complex to design and train relatively large neural channel codes via deep learning techniques. Consequently, most of the results in the literature are limited to relatively short codes having less than 100 information bits. In this paper, we construct ProductAEs, a computationally efficient family of deep-learning driven (encoder, decoder) pairs, that aim at enabling the training of relatively large channel codes (both encoders and decoders) with a manageable training complexity. We build upon the ideas from classical product codes, and propose constructing large neural codes using smaller code components. More specifically, instead of directly training the encoder and decoder for a large neural code of dimension $k$ and blocklength $n$, we provide a framework that requires training neural encoders and decoders for the code parameters $(n_1,k_1)$ and $(n_2,k_2)$ such that $n_1 n_2=n$ and $k_1 k_2=k$. Our training results show significant gains, over all ranges of signal-to-noise ratio (SNR), for a code of parameters $(225,100)$ and a moderate-length code of parameters $(441,196)$, over polar codes under successive cancellation (SC) decoder. Moreover, our results demonstrate meaningful gains over Turbo Autoencoder (TurboAE) and state-of-the-art classical codes. This is the first work to design product autoencoders and a pioneering work on training large channel codes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
