AI RESEARCH

Quantization of Spiking Neural Networks Beyond Accuracy

arXiv CS.LG

ArXi:2604.14487v1 Announce Type: new Quantization is a natural complement to the sparse, event-driven computation of Spiking Neural Networks, reducing memory bandwidth and arithmetic cost for deployment on resource-constrained hardware. However, existing SNN quantization evaluation focuses almost exclusively on accuracy, overlooking whether a quantized network preserves the firing behavior of its full-precision counterpart.