STCSNN: High energy efficiency spike-train level spiking neural networks with spatio-temporal conversion

TL;DR

This paper introduces STCSNN, an energy-efficient spike-train level spiking neural network with spatio-temporal conversion, achieving high accuracy and low power consumption by novel conversion blocks and a specialized learning rule.

Contribution

The paper proposes a new spiking neural network architecture with spatio-temporal conversion and a tailored learning rule, improving accuracy and energy efficiency over existing models.

Findings

Outperforms state-of-the-art accuracy on multiple datasets

Uses fewer time steps for inference

Demonstrates high energy efficiency

Abstract

Brain-inspired spiking neuron networks (SNNs) have attracted widespread research interest due to their low power features, high biological plausibility, and strong spatiotemporal information processing capability. Although adopting a surrogate gradient (SG) makes the non-differentiability SNN trainable, achieving comparable accuracy for ANNs and keeping low-power features simultaneously is still tricky. In this paper, we proposed an energy-efficient spike-train level spiking neural network with spatio-temporal conversion, which has low computational cost and high accuracy. In the STCSNN, spatio-temporal conversion blocks (STCBs) are proposed to keep the low power features of SNNs and improve accuracy. However, STCSNN cannot adopt backpropagation algorithms directly due to the non-differentiability nature of spike trains. We proposed a suitable learning rule for STCSNNs by deducing the equivalent gradient of STCB. We evaluate the proposed STCSNN on static and neuromorphic datasets, including Fashion-Mnist, Cifar10, Cifar100, TinyImageNet, and DVS-Cifar10. The experiment results show that our proposed STCSNN outperforms the state-of-the-art accuracy on nearly all datasets, using fewer time steps and being highly energy-efficient.