Noise-Robust Deep Spiking Neural Networks with Temporal Information

TL;DR

This paper introduces a noise-robust deep spiking neural network that effectively handles spike deletion and jitter, leveraging temporal information to improve energy efficiency and robustness for real-world neuromorphic applications.

Contribution

The paper presents a novel approach to enhance noise robustness in deep SNNs with temporal coding, addressing a gap in existing research.

Findings

Achieved high robustness to spike deletion and jitter.

Demonstrated improved efficiency in neuromorphic devices.

Validated effectiveness across various neural coding methods.

Abstract

Spiking neural networks (SNNs) have emerged as energy-efficient neural networks with temporal information. SNNs have shown a superior efficiency on neuromorphic devices, but the devices are susceptible to noise, which hinders them from being applied in real-world applications. Several studies have increased noise robustness, but most of them considered neither deep SNNs nor temporal information. In this paper, we investigate the effect of noise on deep SNNs with various neural coding methods and present a noise-robust deep SNN with temporal information. With the proposed methods, we have achieved a deep SNN that is efficient and robust to spike deletion and jitter.