Spiking Neural Networks (SNNs) are considered to have enormous potential in the future development of Artificial Intelligence due to their brain-inspired and energy-efficient properties. Compared to vanilla Spatial-Temporal Back-propagation (STBP) training methods, online training can effectively avoid the risk of GPU memory explosion. However, current online learning frameworks cannot tackle the gradient discrepancy problem between the forward and backward process, merely aiming to optimize the GPU memory, resulting in no performance advantages compared to the STBP-based models in the inference stage. To address the aforementioned challenges, we propose Hybrid-Driven Leaky Integrate-and-Fire (HD-LIF) model family for efficient online learning, which respectively adopt different spiking calculation mechanism in the upper-region and lower-region of the firing threshold. We theoretically point out that our learning framework can effectively separate temporal gradients and address the misalignment problem of surrogate gradients, as well as achieving full-stage optimization towards learning precision, memory complexity and power consumption. Experimental results have demonstrated that our scheme is enable to achieve state-of-the-art performance for multiple evaluation metrics, breaking through the traditional paradigm of SNN online training and deployment. Code is available at \href{https://github.com/hzc1208/HD_LIF}{here}.

翻译：脉冲神经网络因其类脑特性和高能效特性，被认为在人工智能未来发展中具有巨大潜力。与传统的时空反向传播训练方法相比，在线训练能有效避免GPU内存爆炸风险。然而，当前在线学习框架无法解决前向与反向过程的梯度失配问题，仅着眼于GPU内存优化，导致其在推理阶段相比基于STBP的模型不具备性能优势。为应对上述挑战，我们提出用于高效在线学习的混合驱动漏积分发放模型系列，该模型在发放阈值的上、下区域分别采用不同的脉冲计算机制。我们从理论上指出，该学习框架能有效分离时序梯度并解决代理梯度的错位问题，同时实现对学习精度、内存复杂度与功耗的全阶段优化。实验结果表明，本方案在多项评估指标上均能达到最先进性能，突破了传统SNN在线训练与部署范式。代码发布于\href{https://github.com/hzc1208/HD_LIF}{此处}。