We consider a trainable point-to-point communication system, where both transmitter and receiver are implemented as neural networks (NNs), and demonstrate that training on the bit-wise mutual information (BMI) allows seamless integration with practical bit-metric decoding (BMD) receivers, as well as joint optimization of constellation shaping and labeling. Moreover, we present a fully differentiable neural iterative demapping and decoding (IDD) structure which achieves significant gains on additive white Gaussian noise (AWGN) channels using a standard 802.11n low-density parity-check (LDPC) code. The strength of this approach is that it can be applied to arbitrary channels without any modifications. Going one step further, we show that careful code design can lead to further performance improvements. Lastly, we show the viability of the proposed system through implementation on software-defined radios (SDRs) and training of the end-to-end system on the actual wireless channel. Experimental results reveal that the proposed method enables significant gains compared to conventional techniques.

中文翻译：

---

可训练的通信系统：概念和原型

我们考虑了一个可训练的点对点通信系统，其中发射器和接收器都实现为神经网络 (NN)，并证明对逐位互信息 (BMI) 的训练允许与实际的位度量解码无缝集成。 BMD) 接收器，以及星座整形和标记的联合优化。此外，我们提出了一种完全可微的神经迭代解映射和解码 (IDD) 结构，该结构使用标准的 802.11n 低密度奇偶校验 (LDPC) 代码在加性高斯白噪声 (AWGN) 通道上实现了显着增益。这种方法的优势在于它可以应用于任意通道而无需任何修改。更进一步，我们表明仔细的代码设计可以带来进一步的性能改进。最后，我们通过在软件定义无线电 (SDR) 上实施和在实际无线信道上对端到端系统进行培训来展示所提议系统的可行性。实验结果表明，与传统技术相比，所提出的方法可以获得显着的收益。