Spiking neural networks (SNNs), inspired by the neural circuits of the brain, are promising in achieving high computational efficiency with biological fidelity. Nevertheless, it is quite difficult to optimize SNNs because the functional roles of their modelling components remain unclear. By designing and evaluating several variants of the classic model, we systematically investigate the functional roles of key modelling components, leakage, reset, and recurrence, in leaky integrate-and-fire (LIF) based SNNs. Through extensive experiments, we demonstrate how these components influence the accuracy, generalization, and robustness of SNNs. Specifically, we find that the leakage plays a crucial role in balancing memory retention and robustness, the reset mechanism is essential for uninterrupted temporal processing and computational efficiency, and the recurrence enriches the capability to model complex dynamics at a cost of robustness degradation. With these interesting observations, we provide optimization suggestions for enhancing the performance of SNNs in different scenarios. This work deepens the understanding of how SNNs work, which offers valuable guidance for the development of more effective and robust neuromorphic models.

翻译：脉冲神经网络（SNNs）受大脑神经回路启发，有望在保持生物保真度的同时实现高计算效率。然而，由于建模组件的功能作用尚不明确，SNNs的优化面临较大困难。通过设计并评估经典模型的若干变体，我们系统研究了基于泄露积分点火（LIF）的SNNs中关键建模组件（泄露、重置和循环）的功能作用。通过大量实验，我们揭示了这些组件如何影响SNNs的准确性、泛化性和鲁棒性。具体而言：泄露在记忆保留与鲁棒性平衡中起关键作用，重置机制对连续时间处理与计算效率不可或缺，而循环虽增强了复杂动态建模能力，但以牺牲鲁棒性为代价。基于这些有趣发现，我们提出了提升SNNs在不同场景下性能的优化建议。本研究深化了对SNNs工作机制的理解，为开发更高效、更鲁棒的神经形态模型提供了宝贵指导。