EUVIMEDEUVIMED entdecken
Crossref

Universality of the mean-field equations of networks of Hopfield-like neurons

Olivier Faugeras, Etienne Tanré

Journal of Mathematical Biology · 2025

DOI: 10.1007/s00285-025-02271-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Mathematical Biology, 2025. Verfasst von Olivier Faugeras und 1 weiteren Autor:innen. Beteiligte Einrichtung: Université Côte D'Azur, Inria, 2004, route des Lucioles, BP 93, 06902, Sophia Antipolis Cedex, France. Hauptthemen laut MEDLINE: Models, Neurological, Neurons, Nerve Net. Die Arbeit nennt 29 Literaturangaben. Gefördert von: Agence Nationale de la Recherche.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We revisit the problem of characterising the mean-field limit of a network of Hopfield-like neurons. Building on the previous works of Ben Arous and Guionnet we establish for a large class of networks of Hopfield-like neurons, i.e. rate neurons, the mean-field equations on a time interval [ 0 , T ] , T > 0 , of the thermodynamic limit of these networks, i.e. the limit when the number of neurons goes to infinity. Here, we do not assume that the synaptic weights describing the connections between the neurons are i.i.d. as zero-mean Gaussians. The limit equations are stochastic and very simply described in terms of two functions, a "correlation" function noted K Q ( t , s ) and a "mean" function noted m Q ( t ) . The "noise" part of the equations is a linear function of the Brownian motion, which is obtained by solving a Volterra equation of the second kind whose resolving kernel is expressed as a function of K Q . We give a constructive proof of the uniqueness of the limit equations. We use the corresponding algorithm for an effective computation of the functions K Q and m Q , given the weights distribution. Several numerical experiments are reported.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Models, NeurologicalNeuronsNerve NetAlgorithmsStochastic ProcessesAnimalsMathematical ConceptsComputer SimulationHumans

Stichwörter der Autor:innen

Girsanov transformHopfield Neural networkInteracting Particle SystemLarge deviations

Autor:innen und Institutionen

  • Université Côte D'Azur, Inria, 2004, route des Lucioles, BP 93, 06902, Sophia Antipolis Cedex, France.
  • Université Côte D'Azur, Inria, CNRS, LJAD, Parc Valrose, 06108, NICE Cedex 2, France. Etienne.Tanre@inria.fr.

Förderung

  • Agence Nationale de la Recherche

Zitieren

APA

Faugeras, O., & Tanré, E. (2025). Universality of the mean-field equations of networks of Hopfield-like neurons. Journal of Mathematical Biology. https://doi.org/10.1007/s00285-025-02271-4

Vancouver

Faugeras O, Tanré E. Universality of the mean-field equations of networks of Hopfield-like neurons. Journal of Mathematical Biology. 2025. doi:10.1007/s00285-025-02271-4

BibTeX
@article{Faugeras2025,
  author = {Faugeras, Olivier and Tanré, Etienne},
  title = {Universality of the mean-field equations of networks of Hopfield-like neurons},
  journal = {Journal of Mathematical Biology},
  year = {2025},
  doi = {10.1007/s00285-025-02271-4}
}
Kostenlos starten →