Direct Training High-Performance Deep Spiking Neural Networks: A Review of Theories and Methods

TL;DR

This review paper systematically summarizes recent theories, methods, and advancements in training deep spiking neural networks, highlighting their high performance, diverse architectures, and potential for energy-efficient computation.

Contribution

It provides a comprehensive overview of the latest developments in training deep SNNs, including theoretical foundations, models, hardware, and future trends.

Findings

Deep SNNs have achieved high performance on large-scale datasets.

Transformer-based SNNs show comparable results to ANNs.

Advances in surrogate gradient methods enable effective training of deep SNNs.

Abstract

Spiking neural networks (SNNs) offer a promising energy-efficient alternative to artificial neural networks (ANNs), in virtue of their high biological plausibility, rich spatial-temporal dynamics, and event-driven computation. The direct training algorithms based on the surrogate gradient method provide sufficient flexibility to design novel SNN architectures and explore the spatial-temporal dynamics of SNNs. According to previous studies, the performance of models is highly dependent on their sizes. Recently, direct training deep SNNs have achieved great progress on both neuromorphic datasets and large-scale static datasets. Notably, transformer-based SNNs show comparable performance with their ANN counterparts. In this paper, we provide a new perspective to summarize the theories and methods for training deep SNNs with high performance in a systematic and comprehensive way, including theory fundamentals, spiking neuron models, advanced SNN models and residual architectures, software frameworks and neuromorphic hardware, applications, and future trends. The reviewed papers are collected at https://github.com/zhouchenlin2096/Awesome-Spiking-Neural-Networks