Learning in Wilson-Cowan Model for Metapopulation
Neural Computation · 2025
DOI: 10.1162/neco_a_01744 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Computation, 2025. Verfasst von Raffaele Marino und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy raffaele.marino@unifi.it. Hauptthemen laut MEDLINE: Neural Networks, Computer, Models, Neurological, Brain, Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 100 Literaturangaben. Gefördert von: The Mathematics and Mechanics of Nonlinear Wave Propagation in Solids.
Abstract (Originalsprache)
The Wilson-Cowan model for metapopulation, a neural mass network model, treats different subcortical regions of the brain as connected nodes, with connections representing various types of structural, functional, or effective neuronal connectivity between these regions. Each region comprises interacting populations of excitatory and inhibitory cells, consistent with the standard Wilson-Cowan model. In this article, we show how to incorporate stable attractors into such a metapopulation model’s dynamics. By doing so, we transform the neural mass network model into a biologically inspired learning algorithm capable of solving different classification tasks. We test it on MNIST and Fashion MNIST in combination with convolutional neural networks, as well as on CIFAR-10 and TF-FLOWERS, and in combination with a transformer architecture (BERT) on IMDB, consistently achieving high classification accuracy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy raffaele.marino@unifi.it.
- Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy lorenzo.buffoni@unifi.it.
- Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy lorenzo.chicchi@unifi.it.
- Department of Mathematics and Computer Science, University of Florence, 50134 Florence, Italy fdipatti@gmail.com.
- Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy diego.febbe@unifi.it.
- Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy lorenzo.giambagli@unifi.it.
Förderung
- The Mathematics and Mechanics of Nonlinear Wave Propagation in Solids
Zitieren
APA
Marino, R., Buffoni, L., Chicchi, L., Patti, F. D., Febbe, D., Giambagli, L., & Fanelli, D. (2025). Learning in Wilson-Cowan Model for Metapopulation. Neural Computation. https://doi.org/10.1162/neco_a_01744
Vancouver
Marino R, Buffoni L, Chicchi L, Patti FD, Febbe D, Giambagli L, et al. Learning in Wilson-Cowan Model for Metapopulation. Neural Computation. 2025. doi:10.1162/neco_a_01744
BibTeX
@article{Marino2025,
author = {Marino, Raffaele and Buffoni, Lorenzo and Chicchi, Lorenzo and Patti, Francesca Di and Febbe, Diego and Giambagli, Lorenzo and Fanelli, Duccio},
title = {Learning in Wilson-Cowan Model for Metapopulation},
journal = {Neural Computation},
year = {2025},
doi = {10.1162/neco_a_01744}
}
EUVIMED