Spiking Neural Networks (SNNs), as the third generation of neural networks, have gained prominence for their biological plausibility and computational efficiency, especially in processing diverse datasets. The integration of attention mechanisms, inspired by advancements in neural network architectures, has led to the development of Spiking Transformers. These have shown promise in enhancing SNNs' capabilities, particularly in the realms of both static and neuromorphic datasets. Despite their progress, a discernible gap exists in these systems, specifically in the Spiking Self Attention (SSA) mechanism's effectiveness in leveraging the temporal processing potential of SNNs. To address this, we introduce the Temporal Interaction Module (TIM), a novel, convolution-based enhancement designed to augment the temporal data processing abilities within SNN architectures. TIM's integration into existing SNN frameworks is seamless and efficient, requiring minimal additional parameters while significantly boosting their temporal information handling capabilities. Through rigorous experimentation, TIM has demonstrated its effectiveness in exploiting temporal information, leading to state-of-the-art performance across various neuromorphic datasets.

翻译：脉冲神经网络（SNNs）作为第三代神经网络，因其生物合理性和计算效率而受到广泛关注，尤其是在处理多样化数据集方面。受神经网络架构进展的启发，注意力机制的集成推动了脉冲 Transformer 的发展。这些模型在增强 SNNs 能力方面展现出潜力，特别是在静态数据集和神经形态数据集领域。尽管取得了进展，但这些系统仍存在一个明显的不足，即脉冲自注意力（SSA）机制在利用 SNNs 时间处理潜力方面的有效性有待提升。为解决这一问题，我们引入了时间交互模块（TIM），这是一种基于卷积的新型增强模块，旨在提升 SNN 架构中的时间数据处理能力。TIM 能够无缝且高效地集成到现有 SNN 框架中，仅需少量额外参数，同时显著增强其对时间信息的处理能力。通过严格的实验，TIM 在利用时间信息方面展现了其有效性，并在多种神经形态数据集上取得了最先进的性能。