学习用于噪声信道通信的鲁棒表示
Learning Robust Representations for Communications over Noisy Channels
AI总结:
本文研究端到端通信系统的鲁棒表示学习,比较基于互信息与码字距离的代价函数,并提出受 Barlow Twins 启发的编码器,证明随机噪声功率迭代训练与最小化块错误率效果最佳。
摘要:
我们探索使用 FCNN(全连接神经网络)来设计端到端通信系统,而不从现有经典通信模型或差错控制编码中获取任何灵感。本工作仅依赖信息论和机器学习工具。我们研究了在严格功率约束下,使用基于互信息和码字间成对距离的多种代价函数来生成用于传输的鲁棒表示所产生的影响。此外,我们提出了一种受 Barlow Twins 框架启发的新型编码器结构。结果表明,在最小化块错误率的同时,使用随机选择的噪声功率水平进行迭代训练可提供最佳的差错性能。
英文摘要:
We explore the use of FCNNs (Fully Connected Neural Networks) for designing end-to-end communication systems without taking any inspiration from existing classical communications models or error control coding. This work relies solely on the tools of information theory and machine learning. We investigate the impact of using various cost functions based on mutual information and pairwise distances between codewords to generate robust representations for transmission under strict power constraints. Additionally, we introduce a novel encoder structure inspired by the Barlow Twins framework. Our results show that iterative training with randomly chosen noise power levels while minimizing block error rate provides the best error performance.
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。