提出新方法解析神经网络接收机，揭示信噪比处理关键单元。
Interpreting Deep Neural Network-Based Receiver Under Varying Signal-To-Noise Ratios
- 通过分析卷积神经网络各单元对信道参数的贡献度，定位关键信息单元。
- 实验验证在不同信噪比下，能准确识别对信号处理贡献最大和最小的单元。
- 方法可推广至多种模型，适合通信与高维神经网络解释需求。
我们提出一种新型神经网络解释方法，聚焦于基于卷积神经网络的接收机模型。该方法识别出模型中对目标信道参数信息贡献最大（或最小）的单元，实现全局与局部层面的双重解释——全局解释由局部解释聚合而成。在链路级仿真中，该方法有效识别了对信噪比处理贡献最大和最小的网络单元。尽管研究重点是无线接收机模型，但该方法可推广至其他神经网络架构与应用，在高维场景下仍具备稳健的估计能力。
原文摘要 · Abstract (English)
We propose a novel method for interpreting neural networks, focusing on convolutional neural network-based receiver model. The method identifies which unit or units of the model contain most (or least) information about the channel parameter(s) of the interest, providing insights at both global and local levels -- with global explanations aggregating local ones. Experiments on link-level simulations demonstrate the method's effectiveness in identifying units that contribute most (and least) to signal-to-noise ratio processing. Although we focus on a radio receiver model, the method generalizes to other neural network architectures and applications, offering robust estimation even in high-dimensional settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。