Spiking Neural Networks in Intelligent Edge Computing

Deep neural networks (DNNs) have witnessed rapid advancements and remarkable success in recent years, leading to their increasingly widespread implementation on edge devices. However, the deployment, execution, and life cycle management of traditional artificial neural networks (ANNs) on resource-constrained edge devices present significant challenges. Spiking neural networks (SNNs) are a class of neuroscience-inspired neural networks that emulate the low-power operational mode of biological neurons. SNNs possess advantages such as low power consumption, low latency, event-driven processing, and reduced communication overhead, making them particularly well-suited for edge devices and intelligent edge computing. As a result, they have garnered significant attention in both research and practical applications. In this paper, we present a comprehensive survey of the fundamentals of SNNs and the advancements in SNN research for edge computing, exploring potential applications and future directions in this emerging field. We also present a case study highlighting that SNNs outperform ANNs in distributed learning, achieving a 6% improvement in accuracy and an 80% reduction in data transmission.