Papers › Learning in Wilson-Cowan model for metapopulation

Learning in Wilson-Cowan model for metapopulation

24 Jun 2024arXiv:2406.16453archive 2025-07-28

Raffaele Marino, Lorenzo Buffoni, Lorenzo Chicchi, Francesca Di Patti, Diego Febbe, Lorenzo Giambagli, Duccio Fanelli

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. By incorporating stable attractors into such a metapopulation model's dynamics, we transform it into a learning algorithm capable of achieving high image and text classification accuracy. We test it on MNIST and Fashion MNIST, in combination with convolutional neural networks, on CIFAR-10 and TF-FLOWERS, and, in combination with a transformer architecture (BERT), on IMDB, always showing high classification accuracy. These numerical evaluations illustrate that minimal modifications to the Wilson-Cowan model for metapopulation can reveal unique and previously unobserved dynamics.

Paper PDF Code

Code

raffaelemarino/learning_in_wilsoncowan officialmentioned in papermentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Classification Sentiment Analysis Text Classification model text-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Image Classification	CIFAR-10	CNN+ Wilson-Cowan model RNN	Percentage correct	86.59	#227 of 265	Archive leaderboard	report
Image Classification	Fashion-MNIST	CNN+ Wilson-Cowan model RNN	Accuracy	91.35	#27 of 34	Archive leaderboard	report
Image Classification	Fashion-MNIST	Wilson-Cowan model RNN	Accuracy	88.39	#30 of 34	Archive leaderboard	report
Image Classification	Flowers (Tensorflow)	CNN+ Wilson-Cowan model RNN	Accuracy	84.85	#1 of 1	Archive leaderboard	report
Image Classification	MNIST	CNN+ Wilson-Cowan model RNN	Accuracy	99.31	#68 of 81	Archive leaderboard	report
Image Classification	MNIST	Wilson-Cowan model RNN	Accuracy	98.13	#74 of 81	Archive leaderboard	report
Sentiment Analysis	IMDb	Bert+ Wilson-Cowan model RNN	Accuracy	87.46	#42 of 49	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections