The identification of sensory cues associated with potential opportunities and dangers is frequently complicated by unrelated events that separate useful cues by long delays. As a result, it remains a challenging task for state-of-the-art spiking neural networks (SNNs) to establish long-term temporal dependency between distant cues. To address this challenge, we propose a novel biologically inspired Two-Compartment Leaky Integrate-and-Fire spiking neuron model, dubbed TC-LIF. The proposed model incorporates carefully designed somatic and dendritic compartments that are tailored to facilitate learning long-term temporal dependencies. Furthermore, a theoretical analysis is provided to validate the effectiveness of TC-LIF in propagating error gradients over an extended temporal duration. Our experimental results, on a diverse range of temporal classification tasks, demonstrate superior temporal classification capability, rapid training convergence, and high energy efficiency of the proposed TC-LIF model. Therefore, this work opens up a myriad of opportunities for solving challenging temporal processing tasks on emerging neuromorphic computing systems. Our code is publicly available at https://github.com/ZhangShimin1/TC-LIF.

翻译：识别与潜在机遇和危险相关的感官线索，常常因无关事件将有用线索分隔较长时间而变得复杂。因此，对于最先进的脉冲神经网络（SNNs）而言，建立远距离线索之间的长时时间依赖关系仍是一项具有挑战性的任务。为应对这一挑战，我们提出了一种新颖的、受生物学启发的双房室漏积分点火脉冲神经元模型，称为TC-LIF。该模型包含经过精心设计的胞体和树突房室，专门用于促进长时时间依赖关系的学习。此外，本文提供了理论分析，验证了TC-LIF在长时程内传播误差梯度的有效性。我们在多种时间分类任务上的实验结果表明，所提出的TC-LIF模型具有卓越的时间分类能力、快速的训练收敛速度以及高能效特性。因此，这项工作为在新兴神经形态计算系统上解决具有挑战性的时间处理任务开辟了众多机遇。我们的代码已在https://github.com/ZhangShimin1/TC-LIF上开源。