SDSNN: A Single-Timestep Spiking Neural Network with Self-Dropping Neuron and Bayesian Optimization
This work addresses energy efficiency and latency issues for SNNs in edge computing scenarios, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the high inference latency and energy consumption of multi-timestep Spiking Neural Networks (SNNs) by proposing a single-timestep SNN with a Self-Dropping Neuron mechanism and Bayesian optimization, achieving accuracies of 93.72%, 92.20%, and 69.45% on Fashion-MNIST, CIFAR-10, and CIFAR-100 while reducing energy consumption by 56%, 21%, and 22% compared to traditional SNNs.
Spiking Neural Networks (SNNs), as an emerging biologically inspired computational model, demonstrate significant energy efficiency advantages due to their event-driven information processing mechanism. Compared to traditional Artificial Neural Networks (ANNs), SNNs transmit information through discrete spike signals, which substantially reduces computational energy consumption through their sparse encoding approach. However, the multi-timestep computation model significantly increases inference latency and energy, limiting the applicability of SNNs in edge computing scenarios. We propose a single-timestep SNN, which enhances accuracy and reduces computational energy consumption in a single timestep by optimizing spike generation and temporal parameters. We design a Self-Dropping Neuron mechanism, which enhances information-carrying capacity through dynamic threshold adjustment and selective spike suppression. Furthermore, we employ Bayesian optimization to globally search for time parameters and obtain an efficient inference mode with a single time step. Experimental results on the Fashion-MNIST, CIFAR-10, and CIFAR-100 datasets demonstrate that, compared to traditional multi-timestep SNNs employing the Leaky Integrate-and-Fire (LIF) model, our method achieves classification accuracies of 93.72%, 92.20%, and 69.45%, respectively, using only single-timestep spikes, while maintaining comparable or even superior accuracy. Additionally, it reduces energy consumption by 56%, 21%, and 22%, respectively.