Improving Stability and Performance of Spiking Neural Networks through Enhancing Temporal Consistency

TL;DR

This paper introduces a method to improve the stability and performance of spiking neural networks by enhancing temporal consistency across timesteps, enabling better results on neuromorphic datasets and reducing the need for large simulation timesteps.

Contribution

The authors propose a novel approach to enhance temporal consistency in SNNs, addressing output distribution discrepancies at different timesteps, and achieve state-of-the-art results on neuromorphic datasets.

Findings

Achieved state-of-the-art performance on DVS-CIFAR10 and N-Caltech101.

Comparable performance to other top SNN algorithms on static datasets.

Superior performance in the test phase with timestep T=1.

Abstract

Spiking neural networks have gained significant attention due to their brain-like information processing capabilities. The use of surrogate gradients has made it possible to train spiking neural networks with backpropagation, leading to impressive performance in various tasks. However, spiking neural networks trained with backpropagation typically approximate actual labels using the average output, often necessitating a larger simulation timestep to enhance the network's performance. This delay constraint poses a challenge to the further advancement of SNNs. Current training algorithms tend to overlook the differences in output distribution at various timesteps. Particularly for neuromorphic datasets, inputs at different timesteps can cause inconsistencies in output distribution, leading to a significant deviation from the optimal direction when combining optimization directions from different moments. To tackle this issue, we have designed a method to enhance the temporal consistency of outputs at different timesteps. We have conducted experiments on static datasets such as CIFAR10, CIFAR100, and ImageNet. The results demonstrate that our algorithm can achieve comparable performance to other optimal SNN algorithms. Notably, our algorithm has achieved state-of-the-art performance on neuromorphic datasets DVS-CIFAR10 and N-Caltech101, and can achieve superior performance in the test phase with timestep T=1.