EUVIMEDEUVIMED entdecken
Open Access

Contrastive signal–dependent plasticity: Self-supervised learning in spiking neural circuits

Alexander G Ororbia iD

Science Advances · 2024

DOI: 10.1126/sciadv.adn6076 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, 2024. Verfasst von Alexander G Ororbia. Beteiligte Einrichtung: Department of Computer Science, Rochester Institute of Technology, 1 Lomb Memorial Dr, Rochester, NY 14623, USA. Hauptthemen laut MEDLINE: Neuronal Plasticity, Models, Neurological, Neurons, Neural Networks, Computer. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Brain-inspired machine intelligence research seeks to develop computational models that emulate the information processing and adaptability that distinguishes biological systems of neurons. This has led to the development of spiking neural networks, a class of models that promisingly addresses the biological implausibility and the lack of energy efficiency inherent to modern-day deep neural networks. In this work, we address the challenge of designing neurobiologically motivated schemes for adjusting the synapses of spiking networks and propose contrastive signal–dependent plasticity, a process which generalizes ideas behind self-supervised learning to facilitate local adaptation in architectures of event-based neuronal layers that operate in parallel. Our experimental simulations demonstrate a consistent advantage over other biologically plausible approaches when training recurrent spiking networks, crucially side-stepping the need for extra structure such as feedback synapses.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neuronal PlasticityModels, NeurologicalNeuronsNeural Networks, ComputerSynapsesAction PotentialsNerve NetHumansComputer SimulationSupervised Machine LearningAnimalsAlgorithms

Autor:innen und Institutionen

  • Department of Computer Science, Rochester Institute of Technology, 1 Lomb Memorial Dr, Rochester, NY 14623, USA.

ORCID-Profile: Alexander G Ororbia

Zitieren

APA

Ororbia, A. G. (2024). Contrastive signal–dependent plasticity: Self-supervised learning in spiking neural circuits. Science Advances. https://doi.org/10.1126/sciadv.adn6076

Vancouver

Ororbia AG. Contrastive signal–dependent plasticity: Self-supervised learning in spiking neural circuits. Science Advances. 2024. doi:10.1126/sciadv.adn6076

BibTeX
@article{Ororbia2024,
  author = {Ororbia, Alexander G},
  title = {Contrastive signal–dependent plasticity: Self-supervised learning in spiking neural circuits},
  journal = {Science Advances},
  year = {2024},
  doi = {10.1126/sciadv.adn6076}
}
Kostenlos starten →