Spiking Neural Networks (SNNs), providing more realistic neuronal dynamics, have shown to achieve performance comparable to Artificial Neural Networks (ANNs) in several machine learning tasks. Information is processed as spikes within SNNs in an event-based mechanism that significantly reduces energy consumption. However, training SNNs is challenging due to the non-differentiable nature of the spiking mechanism. Traditional approaches, such as Backpropagation Through Time (BPTT), have shown effectiveness but comes with additional computational and memory costs and are biologically implausible. In contrast, recent works propose alternative learning methods with varying degrees of locality, demonstrating success in classification tasks. In this work, we show that these methods share similarities during the training process, while they present a trade-off between biological plausibility and performance. Further, this research examines the implicitly recurrent nature of SNNs and investigates the influence of addition of explicit recurrence to SNNs. We experimentally prove that the addition of explicit recurrent weights enhances the robustness of SNNs. We also investigate the performance of local learning methods under gradient and non-gradient based adversarial attacks.

翻译：脉冲神经网络（SNN）因其更逼真的神经元动力学特性，在多项机器学习任务中展现出与人工神经网络（ANN）相当的性能。SNN采用基于事件的处理机制传递信息，能显著降低能耗。然而，由于脉冲机制的非可微特性，训练SNN存在巨大挑战。传统方法如时间反向传播（BPTT）虽有效，但会带来额外计算与存储开销，且缺乏生物合理性。相比之下，近期研究提出了具有不同局部性程度的替代学习方法，在分类任务中取得良好效果。本研究表明，这些方法在训练过程中具有相似性，但在生物合理性与性能之间存在权衡。进一步地，本研究深入剖析了SNN的隐式循环特性，并探究了显式循环结构对SNN的影响。实验证明，添加显式循环权重可增强SNN的鲁棒性。此外，我们系统评估了局部学习方法在基于梯度与非梯度的对抗攻击下的性能表现。