Evolutionary Spiking Neural Networks: A Survey

TL;DR

This survey reviews recent advances in evolutionary methods for designing energy-efficient spiking neural networks, highlighting their potential to overcome traditional training challenges and improve performance.

Contribution

It provides a comprehensive overview of evolutionary approaches in SNNs and discusses future challenges and directions in this emerging field.

Findings

Evolutionary methods enable energy-efficient SNN architectures.

Recent approaches achieve high performance on machine learning benchmarks.

Survey highlights key challenges and future research directions.

Abstract

Spiking neural networks (SNNs) are gaining increasing attention as potential computationally efficient alternatives to traditional artificial neural networks(ANNs). However, the unique information propagation mechanisms and the complexity of SNN neuron models pose challenges for adopting traditional methods developed for ANNs to SNNs. These challenges include both weight learning and architecture design. While surrogate gradient learning has shown some success in addressing the former challenge, the latter remains relatively unexplored. Recently, a novel paradigm utilizing evolutionary computation methods has emerged to tackle these challenges. This approach has resulted in the development of a variety of energy-efficient and high-performance SNNs across a wide range of machine learning benchmarks. In this paper, we present a survey of these works and initiate discussions on potential challenges ahead.