神经元联合信源-信道编码
Neural Joint Source-Channel Coding
摘要:
为了在有噪声的通信信道上进行可靠的传输,信息论的经典结果表明,将信源和信道编码过程分离出来是渐近最优的。然而,这种分解在有限位长的情况下可能达不到要求,因为它需要对手工代码进行非平凡的调整,并且假设解码的计算能力是无限的。在这项工作中,我们提出了共同学习的编码和解码过程中使用一个新的离散变分自编码器模型。通过在训练过程中向潜在代码中添加噪声来模拟信道,我们可以在给定固定位长和计算预算的情况下学习压缩和纠错。我们获得的代码,不仅是竞争力对几个分离方案,但也学习有用的强大的表示数据的下游任务,如分类。最后,推理摊销产生了一个非常快的神经解码器,几乎比基于迭代置信传播的标准解码方法快一个数量级。
英文摘要:
For reliable transmission across a noisy communication channel, classical results from information theory show that it is asymptotically optimal to separate out the source and channel coding processes. However, this decomposition can fall short in the finite bit-length regime, as it requires non-trivial tuning of hand-crafted codes and assumes infinite computational power for decoding. In this work, we propose to jointly learn the encoding and decoding processes using a new discrete variational autoencoder model. By adding noise into the latent codes to simulate the channel during training, we learn to both compress and error-correct given a fixed bit-length and computational budget. We obtain codes that are not only competitive against several separation schemes, but also learn useful robust representations of the data for downstream tasks such as classification. Finally, inference amortization yields an extremely fast neural decoder, almost an order of magnitude faster compared to standard decoding methods based on iterative belief propagation.
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。