Direct-to-Event Spiking Neural Network Transfer
For researchers and practitioners deploying SNNs on energy-constrained neuromorphic hardware, this work addresses the underexplored problem of transferring direct-coded SNNs to event-based computation.
This paper investigates how to convert a spiking neural network pretrained with direct coding into an event-based representation to improve energy efficiency, proposing methods that achieve comparable performance while reducing energy consumption.
Spiking Neural Networks (SNNs) have gained increasing attention due to their potential for low-power computation on neuromorphic hardware. A widely adopted training strategy for SNNs is direct coding, which enable backpropagation on neuron implementations using continuous-valued surrogate activations. However, recent studies have shown that direct-coded SNNs remain substantially less energy-efficient than their event-based counterparts, limiting their practical deployment in energy sensitive scenarios. Still, to promote the reusability of pretrained SNN database on direct code, this motivates an important yet underexplored question: How can a SNN pretrained with direct code be effectively converted into an event-based representation? In this research, we present the first systematic investigation into this transfer problem, analyze the key challenges that arise when transitioning from direct-coded to event-based computation and propose a set of methods to enable energy-efficient transfer while preserving model performance.