Spiking neural networks (SNNs) represent a promising approach to developing artificial neural networks that are both energy-efficient and biologically plausible. However, applying SNNs to sequential tasks, such as text classification and time-series forecasting, has been hindered by the challenge of creating an effective and hardware-friendly spike-form positional encoding (PE) strategy. Drawing inspiration from the central pattern generators (CPGs) in the human brain, which produce rhythmic patterned outputs without requiring rhythmic inputs, we propose a novel PE technique for SNNs, termed CPG-PE. We demonstrate that the commonly used sinusoidal PE is mathematically a specific solution to the membrane potential dynamics of a particular CPG. Moreover, extensive experiments across various domains, including time-series forecasting, natural language processing, and image classification, show that SNNs with CPG-PE outperform their conventional counterparts. Additionally, we perform analysis experiments to elucidate the mechanism through which SNNs encode positional information and to explore the function of CPGs in the human brain. This investigation may offer valuable insights into the fundamental principles of neural computation.

翻译：脉冲神经网络（SNNs）为开发兼具高能效与生物合理性的新型人工神经网络提供了一条极具前景的技术路径。然而，将其应用于文本分类、时间序列预测等序列任务时，如何构建一种高效且硬件友好的脉冲式位置编码（PE）策略一直是关键挑战。受人类大脑中无需节律性输入即可产生节律性模式输出的中枢模式发生器（CPGs）启发，我们提出了一种面向SNNs的新型位置编码技术——CPG-PE。我们通过理论推导证明，目前广泛使用的正弦位置编码在数学上可视为特定CPG膜电位动力学方程的一个特解。此外，我们在时间序列预测、自然语言处理和图像分类等多个领域的系统性实验表明，采用CPG-PE的SNNs模型性能显著优于传统SNNs。我们还通过机理分析实验，揭示了SNNs编码位置信息的内在机制，并探讨了CPGs在人脑中的功能特性。这项研究有望为神经计算的基本原理提供有价值的理论洞见。