Baronig Maximilian, Ferrand Romain, Sabathiel Silvester, Legenstein Robert
Institute of Machine Learning and Neural Computation, Graz University of Technology, Graz, Austria.
TU Graz-SAL Dependable Embedded Systems Lab, Silicon Austria Labs, Graz, Austria.
Nat Commun. 2025 Jul 1;16(1):5776. doi: 10.1038/s41467-025-60878-z.
Implementations of spiking neural networks on neuromorphic hardware promise orders of magnitude less power consumption than their non-spiking counterparts. The standard neuron model for spike-based computation on such systems has long been the leaky integrate-and-fire neuron. A computationally light augmentation of this neuron model with an adaptation mechanism has recently been shown to exhibit superior performance on spatio-temporal processing tasks. The root of the superiority of these so-called adaptive leaky integrate-and-fire neurons however is not well understood. In this article, we thoroughly analyze the dynamical, computational, and learning properties of adaptive leaky integrate-and-fire neurons and networks thereof. Our investigation reveals significant challenges related to stability and parameterization when employing the conventional Euler-Forward discretization for this class of models. We report a rigorous theoretical and empirical demonstration that these challenges can be effectively addressed by adopting an alternative discretization approach - the Symplectic Euler method, allowing to improve over state-of-the-art performances on common event-based benchmark datasets. Our further analysis of the computational properties of these networks shows that they are particularly well suited to exploit the spatio-temporal structure of input sequences without any normalization techniques.
在神经形态硬件上实现脉冲神经网络有望比非脉冲神经网络消耗的功率降低几个数量级。长期以来，这种系统上基于脉冲进行计算的标准神经元模型一直是泄漏积分发放神经元。最近研究表明，通过一种自适应机制对这种神经元模型进行轻量级计算增强后，在时空处理任务中表现出卓越性能。然而，这些所谓的自适应泄漏积分发放神经元优越性的根源尚未得到很好的理解。在本文中，我们深入分析了自适应泄漏积分发放神经元及其网络的动力学、计算和学习特性。我们的研究揭示了在对这类模型采用传统的欧拉向前离散化时，与稳定性和参数化相关的重大挑战。我们报告了一项严谨的理论和实证证明，即通过采用一种替代离散化方法——辛欧拉方法，可以有效应对这些挑战，从而在基于常见事件的基准数据集上超越当前的先进性能。我们对这些网络计算特性的进一步分析表明，它们特别适合在不使用任何归一化技术的情况下利用输入序列的时空结构。
