Event-Driven Learning for Spiking Neural Networks

arXiv:2403.00270v1 Announce Type: cross
Abstract: Brain-inspired spiking neural networks (SNNs) have gained prominence in the field of neuromorphic computing owing to their low energy consumption during feedforward inference on neuromorphic hardware. However, it remains an open challenge how to effectively benefit from the sparse event-driven property of SNNs to minimize backpropagation learning costs. In this paper, we conduct a comprehensive examination of the existing event-driven learning algorithms, reveal their limitations, and propose novel solutions to overcome them. Specifically, we introduce …

abstract arxiv backpropagation benefit brain brain-inspired challenge computing consumption costs cs.cv cs.ne energy event hardware inference low networks neural networks neuromorphic neuromorphic computing property spiking neural networks type