Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities
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 tha...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/6/3037 |
_version_ | 1797609052410216448 |
---|---|
author | Paweł Pietrzak Szymon Szczęsny Damian Huderek Łukasz Przyborowski |
author_facet | Paweł Pietrzak Szymon Szczęsny Damian Huderek Łukasz Przyborowski |
author_sort | Paweł Pietrzak |
collection | DOAJ |
description | 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. |
first_indexed | 2024-03-11T05:56:07Z |
format | Article |
id | doaj.art-4548af8e4e9e48e1a39a3d2a874eba1b |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T05:56:07Z |
publishDate | 2023-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-4548af8e4e9e48e1a39a3d2a874eba1b2023-11-17T13:45:05ZengMDPI AGSensors1424-82202023-03-01236303710.3390/s23063037Overview of Spiking Neural Network Learning Approaches and Their Computational ComplexitiesPaweł Pietrzak0Szymon Szczęsny1Damian Huderek2Łukasz Przyborowski3Institute of Computing Science, Faculty of Computing and Telecommunications, Poznan University of Technology, Piotrowo 3A Street, 61-138 Poznań, PolandInstitute of Computing Science, Faculty of Computing and Telecommunications, Poznan University of Technology, Piotrowo 3A Street, 61-138 Poznań, PolandInstitute of Computing Science, Faculty of Computing and Telecommunications, Poznan University of Technology, Piotrowo 3A Street, 61-138 Poznań, PolandInstitute of Computing Science, Faculty of Computing and Telecommunications, Poznan University of Technology, Piotrowo 3A Street, 61-138 Poznań, PolandSpiking 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.https://www.mdpi.com/1424-8220/23/6/3037spiking neural networkslearning algorithmscomputational complexityhardware |
spellingShingle | Paweł Pietrzak Szymon Szczęsny Damian Huderek Łukasz Przyborowski Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities Sensors spiking neural networks learning algorithms computational complexity hardware |
title | Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities |
title_full | Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities |
title_fullStr | Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities |
title_full_unstemmed | Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities |
title_short | Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities |
title_sort | overview of spiking neural network learning approaches and their computational complexities |
topic | spiking neural networks learning algorithms computational complexity hardware |
url | https://www.mdpi.com/1424-8220/23/6/3037 |
work_keys_str_mv | AT pawełpietrzak overviewofspikingneuralnetworklearningapproachesandtheircomputationalcomplexities AT szymonszczesny overviewofspikingneuralnetworklearningapproachesandtheircomputationalcomplexities AT damianhuderek overviewofspikingneuralnetworklearningapproachesandtheircomputationalcomplexities AT łukaszprzyborowski overviewofspikingneuralnetworklearningapproachesandtheircomputationalcomplexities |