» Articles » PMID: 36991750

Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities

Overview
Journal Sensors (Basel)
Publisher MDPI
Specialty Biotechnology
Date 2023 Mar 30
PMID 36991750
Authors
Affiliations
Soon will be listed here.
Abstract

Spiking neural networks (SNNs) are subjects of a topic that is gaining more and more interest nowadays. They more closely resemble actual neural networks in the brain than their second-generation counterparts, artificial neural networks (ANNs). SNNs have the potential to be more energy efficient than ANNs on event-driven neuromorphic hardware. This can yield drastic maintenance cost reduction for neural network models, as the energy consumption would be much lower in comparison to regular deep learning models hosted in the cloud today. However, such hardware is still not yet widely available. On standard computer architectures consisting mainly of central processing units (CPUs) and graphics processing units (GPUs) ANNs, due to simpler models of neurons and simpler models of connections between neurons, have the upper hand in terms of execution speed. In general, they also win in terms of learning algorithms, as SNNs do not reach the same levels of performance as their second-generation counterparts in typical machine learning benchmark tasks, such as classification. In this paper, we review existing learning algorithms for spiking neural networks, divide them into categories by type, and assess their computational complexity.

Citing Articles

Developing a brain inspired multilobar neural networks architecture for rapidly and accurately estimating concrete compressive strength.

Alibrahim B, Habib A, Habib M Sci Rep. 2025; 15(1):1989.

PMID: 39814764 PMC: 11735981. DOI: 10.1038/s41598-024-84325-z.


Brain-inspired biomimetic robot control: a review.

Mompo Alepuz A, Papageorgiou D, Tolu S Front Neurorobot. 2024; 18:1395617.

PMID: 39224906 PMC: 11366706. DOI: 10.3389/fnbot.2024.1395617.


A Novel Robotic Controller Using Neural Engineering Framework-Based Spiking Neural Networks.

Marrero D, Kern J, Urrea C Sensors (Basel). 2024; 24(2).

PMID: 38257584 PMC: 10819625. DOI: 10.3390/s24020491.


Moiré synaptic transistor with room-temperature neuromorphic functionality.

Yan X, Zheng Z, Sangwan V, Qian J, Wang X, Liu S Nature. 2023; 624(7992):551-556.

PMID: 38123805 DOI: 10.1038/s41586-023-06791-1.


The computational power of the human brain.

Gebicke-Haerter P Front Cell Neurosci. 2023; 17:1220030.

PMID: 37608987 PMC: 10441807. DOI: 10.3389/fncel.2023.1220030.

References
1.
Lobov S, Zharinov A, Makarov V, Kazantsev V . Spatial Memory in a Spiking Neural Network with Robot Embodiment. Sensors (Basel). 2021; 21(8). PMC: 8070389. DOI: 10.3390/s21082678. View

2.
Rueckauer B, Lungu I, Hu Y, Pfeiffer M, Liu S . Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification. Front Neurosci. 2018; 11:682. PMC: 5770641. DOI: 10.3389/fnins.2017.00682. View

3.
Szczesny S, Huderek D, Przyborowski L . Spiking Neural Network with Linear Computational Complexity for Waveform Analysis in Amperometry. Sensors (Basel). 2021; 21(9). PMC: 8125990. DOI: 10.3390/s21093276. View

4.
Zenke F, Ganguli S . SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks. Neural Comput. 2018; 30(6):1514-1541. PMC: 6118408. DOI: 10.1162/neco_a_01086. View

5.
Yousefzadeh A, Stromatias E, Soto M, Serrano-Gotarredona T, Linares-Barranco B . On Practical Issues for Stochastic STDP Hardware With 1-bit Synaptic Weights. Front Neurosci. 2018; 12:665. PMC: 6196279. DOI: 10.3389/fnins.2018.00665. View