Learning in Wilson-Cowan Model for Metapopulation.

Journal: Neural computation
PMID:

Abstract

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.

Authors

  • Raffaele Marino
    Physics Department, Università degli Studi di Firenze, Via Sansone 1, Firenze, 50019, Italy.
  • Lorenzo Buffoni
    Department of Physics and Astrophysics, University of Florence, Florence, Italy.
  • Lorenzo Chicchi
    CSDC, Department of Physics and Astronomy, University of Florence, Sesto Fiorentino, Italy.
  • Francesca Di Patti
    Department of Mathematics and Computer Science, University of Florence, 50134 Florence, Italy fdipatti@gmail.com.
  • Diego Febbe
    Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy diego.febbe@unifi.it.
  • Lorenzo Giambagli
    CSDC, Department of Physics and Astronomy, University of Florence, Sesto Fiorentino, Italy.
  • Duccio Fanelli
    Department of Physics and Astrophysics, University of Florence, Florence, Italy.