Models Developed for Spiking Neural Networks

TL;DR

This paper reviews the development and performance of spiking neural networks (SNNs) in image classification, highlighting their potential for complex tasks and energy efficiency, and discusses simple learning rules as alternatives to backpropagation.

Contribution

It provides a comprehensive review of SNN structures and their performance, emphasizing their potential in complex machine learning tasks and proposing simple learning rules as alternatives to backpropagation.

Findings

SNNs show promise for complex image classification tasks.

Simple learning rules like STDP can replace backpropagation.

SNNs are energy-efficient and suitable for real-world applications.

Abstract

Emergence of deep neural networks (DNNs) has raised enormous attention towards artificial neural networks (ANNs) once again. They have become the state-of-the-art models and have won different machine learning challenges. Although these networks are inspired by the brain, they lack biological plausibility, and they have structural differences compared to the brain. Spiking neural networks (SNNs) have been around for a long time, and they have been investigated to understand the dynamics of the brain. However, their application in real-world and complicated machine learning tasks were limited. Recently, they have shown great potential in solving such tasks. Due to their energy efficiency and temporal dynamics there are many promises in their future development. In this work, we reviewed the structures and performances of SNNs on image classification tasks. The comparisons illustrate that these networks show great capabilities for more complicated problems. Furthermore, the simple learning rules developed for SNNs, such as STDP and R-STDP, can be a potential alternative to replace the backpropagation algorithm used in DNNs.