发表机构
University of Padova（帕多瓦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对脉冲神经网络层间通信冗余问题，提出预测编码层（误差单元与预测抑制）以动态门控脉冲，在N-MNIST和SHD上通信减少三倍且精度提升。
AI 中文摘要
前馈脉冲神经网络（SNNs）通常不加区分地传播每一个生成的脉冲，而不考虑从信息论角度看这些信息是否冗余。这种缺乏选择性的做法导致层间通信存在高度冗余，从而产生昂贵的开销，例如在多核神经形态硬件或通信主导的物联网（IoT）场景中，特征通过无线方式传输。为应对这一挑战，我们以局部处理换取更精简的网络通道，引入了一种用于SNNs的最小预测编码框架。我们提出了两种共享预测器块的层变体：误差单元，传输带符号的脉冲残差；以及预测抑制，利用残差幅度动态门控并仅前传不可预测的“意外”活动。在N-MNIST和Spiking Heidelberg Digits（SHD）数据集上，使用将局部处理与跨层通信解耦的诊断指标进行评估，我们的新预测编码层实现了显著的通信节省。数值结果显示，通信活动减少三倍，同时两个数据集的任务准确率均有所提升。后一发现值得注意，表明预测编码层不仅最小化通信开销，还产生具有更高表示能力的输出特征向量。
英文摘要
Feedforward Spiking Neural Networks (SNNs) typically propagate every generated spike indiscriminately, disregarding whether the information is redundant from an information-theoretic perspective. This lack of selectivity induces high redundancy in inter-layer communication, creating an expensive overhead, e.g., in scenarios involving many-core neuromorphic hardware or communication-dominated Internet-of-Things (IoT) where features are transmitted wirelessly. To address this challenge, we trade localized processing for leaner network channels by introducing a minimal predictive coding framework for SNNs. We propose two layer variants sharing a predictor block: error units, which transmit signed spiking residuals, and predictive suppression, which uses residual magnitude to dynamically gate and forward only unpredictable, "surprising" activity. Evaluated on the N-MNIST and Spiking Heidelberg Digits (SHD) datasets using diagnostic metrics that decouple local processing from cross-layer communication, our new predictive coding layers achieve significant communication savings. Numerical results reveal a three-fold reduction in communicated activity, while increasing the task accuracy for both datasets. The latter finding is notable, and suggests that predictive coding layers not only minimize communication overhead, but also produce output feature vectors with a higher representation power.
Comments6 pages, 5 figures. Accepted at the 1st Neuromorphic Physical Layer Signal Processing for Wireless Systems Workshop (NeuroPHY 2026), co-located with EWSN 2026
Journal refProceedings of the 2026 International Conference on Embedded Wireless Systems and Networks (EWSN '26), pp. 309-314, 2026
