用卷积增强脉冲GRU，更好处理时空序列数据。
Convolutional Spiking-based GRU Cell for Spatio-temporal Data
- 结合卷积与脉冲神经元，保留局部结构细节。
- 在多个数据集上平均比现有方法高4.35%准确率。
- 适合需要高效处理事件驱动数据的研究者。
基于脉冲的时间信息传递使脉冲神经网络（SNN）能够高效处理纯时间序列或事件驱动的时空数据。将SNN与门控循环单元（GRU）结合，可构建稳健的序列数据处理框架；然而，传统RNN在处理长序列时常丢失局部细节。此前的SpikGRU等方法无法捕捉事件驱动时空数据中的细粒度局部依赖。本文提出卷积脉冲GRU（CS-GRU）单元，利用卷积操作保持局部结构与依赖关系，同时融合脉冲神经元的时间精度与GRU的高效门控机制。该架构在时间数据集（NTIDIGITS、SHD）和时空基准（MNIST、DVSGesture、CIFAR10DVS）上均表现优异。实验表明，CS-GRU平均比先进GRU变体提升4.35%，在序列任务中准确率超90%，最高达99.31%（MNIST）。相比SpikGRU，其效率提升69%。代码已公开于：https://github.com/YesmineAbdennadher/CS-GRU。
原文摘要 · Abstract (English)
Spike-based temporal messaging enables SNNs to efficiently process both purely temporal and spatio-temporal time-series or event-driven data. Combining SNNs with Gated Recurrent Units (GRUs), a variant of recurrent neural networks, gives rise to a robust framework for sequential data processing; however, traditional RNNs often lose local details when handling long sequences. Previous approaches, such as SpikGRU, fail to capture fine-grained local dependencies in event-based spatio-temporal data. In this paper, we introduce the Convolutional Spiking GRU (CS-GRU) cell, which leverages convolutional operations to preserve local structure and dependencies while integrating the temporal precision of spiking neurons with the efficient gating mechanisms of GRUs. This versatile architecture excels on both temporal datasets (NTIDIGITS, SHD) and spatio-temporal benchmarks (MNIST, DVSGesture, CIFAR10DVS). Our experiments show that CS-GRU outperforms state-of-the-art GRU variants by an average of 4.35%, achieving over 90% accuracy on sequential tasks and up to 99.31% on MNIST. It is worth noting that our solution achieves 69% higher efficiency compared to SpikGRU. The code is available at: https://github.com/YesmineAbdennadher/CS-GRU.
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。