EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities

Paweł Pietrzak iD, Szymon Szczęsny iD, Damian Huderek iD, Łukasz Przyborowski iD

Sensors · 11.03.2023 · 23 (6) · 3037

DOI: 10.3390/s23063037 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 11.03.2023. Verfasst von Paweł Pietrzak und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Computing Science, Faculty of Computing and Telecommunications, Poznan University of Technology, Piotrowo 3A Street, 61-138 Poznań, Pola…. Hauptthemen laut MEDLINE: Neural Networks, Computer, Algorithms. Die Arbeit wurde bisher 56-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Poznań University of Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerAlgorithmsHumansAction PotentialsComputersBrain

Stichwörter der Autor:innen

computational complexityhardwarelearning algorithmsspiking neural networks

Autor:innen und Institutionen

  • Institute of Computing Science, Faculty of Computing and Telecommunications, Poznan University of Technology, Piotrowo 3A Street, 61-138 Poznań, Poland.

ORCID-Profile: Paweł Pietrzak, Szymon Szczęsny, Damian Huderek, Łukasz Przyborowski

Förderung

  • Poznań University of Technology

Zitieren

APA

Pietrzak, P., Szczęsny, S., Huderek, D., & Przyborowski, Ł. (2023). Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities. Sensors, 23(6), 3037. https://doi.org/10.3390/s23063037

Vancouver

Pietrzak P, Szczęsny S, Huderek D, Przyborowski Ł. Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities. Sensors. 2023;23(6):3037. doi:10.3390/s23063037

BibTeX
@article{Pietrzak2023,
  author = {Pietrzak, Paweł and Szczęsny, Szymon and Huderek, Damian and Przyborowski, Łukasz},
  title = {Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {6},
  pages = {3037},
  doi = {10.3390/s23063037}
}
Kostenlos starten →