The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks
The Dormant Spiking Neuron (DSN) model introduces a state-driven mechanism allowing neurons to enter a dormant state when their membrane potential drops below a negative threshold. This dynamically prunes redundant computations at the instance level, significantly reducing computational energy by 40% to over 70% while maintaining competitive accuracy on static and neuromorphic datasets.