Multi-state spiking neurons combine sparse binary activations with rich second-order nonlinear recurrent dynamics, making them a promising alternative to standard deep learning models. However, gradient propagation through these dynamics often leads to instabilities that hinder scalability and performance. Inspired by the stable training and strong performance of state space models (SSMs) on long sequences, we introduce two SSM-inspired Leaky Integrate-and-Fire (SiLIF) neuron models. The first extends a two-state neuron with a learnable discretization timestep and logarithmic reparametrization, while the second additionally incorporates the initialization scheme and structure of complex-state SSMs, enabling oscillatory regimes. Our two SiLIF models achieve new state-of-the-art performance among spiking neuron models on both event-based and raw-audio speech recognition datasets. We further demonstrate a favorable performance-efficiency trade-off compared to SSMs, even surpassing them while using half the computational cost through the use of synaptic delays. Our code is available at https://github.com/Maxtimer97/SSM-inspired-LIF.

翻译：多状态脉冲神经元将稀疏二值激活与丰富的二阶非线性循环动力学相结合，成为标准深度学习模型的有前景替代方案。然而，通过此类动力学的梯度传播常导致阻碍可扩展性与性能的不稳定性。受状态空间模型在长序列任务中稳定训练与优异表现的启发，我们提出两种受SSM启发的漏积分点火神经元模型。第一种模型通过可学习离散化时间步长与对数重参数化扩展双状态神经元，第二种模型则进一步融合复杂状态SSM的初始化方案与结构特性，从而支持振荡机制。在基于事件与原始音频的语音识别数据集上，两种SiLIF模型均取得脉冲神经元模型的最新最优性能。我们进一步展示了相较于SSM的性能-效率权衡优势：通过引入突触延迟，SiLIF模型在计算成本减半的情况下甚至超越SSM。代码已开源在https://github.com/Maxtimer97/SSM-inspired-LIF。