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的二进制激活与丰富的二阶非线性循环动力学相结合，使其成为标准深度学习模型的有前景的替代方案。然而，通过这些动力学进行梯度传播常常导致不稳定性，从而阻碍了可扩展性和性能。受状态空间模型（SSMs）在长序列上稳定训练和强大性能的启发，我们引入了两种受SSM启发的泄漏积分发放（SiLIF）神经元模型。第一种模型通过可学习的离散化时间步长和对数重参数化扩展了双状态神经元；而第二种模型额外结合了复数状态SSMs的初始化方案和结构，从而能够实现振荡机制。我们的两种SiLIF模型在基于事件的语音识别数据集和原始音频语音识别数据集上，均实现了脉冲神经元模型中新的最先进性能。我们进一步展示了与SSMs相比更优的性能-效率权衡，甚至通过使用突触延迟，在仅使用一半计算成本的情况下超越了它们。我们的代码可在 https://github.com/Maxtimer97/SSM-inspired-LIF 获取。