Understanding the Functional Roles of Modelling Components in Spiking Neural Networks

arXiv:2403.16674v1 Announce Type: cross
Abstract: Spiking neural networks (SNNs), inspired by the neural circuits of the brain, are promising in achieving high computational efficiency with biological fidelity. Nevertheless, it is quite difficult to optimize SNNs because the functional roles of their modelling components remain unclear. By designing and evaluating several variants of the classic model, we systematically investigate the functional roles of key modelling components, leakage, reset, and recurrence, in leaky integrate-and-fire (LIF) based SNNs. Through extensive experiments, we demonstrate …

abstract arxiv brain circuits components computational cs.ai cs.lg cs.ne designing efficiency fidelity functional modelling networks neural networks roles spiking neural networks type understanding