CHANI: Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2024

CHANI: Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration

Résumé

The present work aims at proving mathematically that a neural network inspired by biology can learn a classification task thanks to local transformations only. In this purpose, we propose a spiking neural network named CHANI (Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration), whose neurons activity is modeled by Hawkes processes. Synaptic weights are updated thanks to an expert aggregation algorithm, providing a local and simple learning rule. We were able to prove that our network can learn on average and asymptotically. Moreover, we demonstrated that it automatically produces neuronal assemblies in the sense that the network can encode several classes and that a same neuron in the intermediate layers might be activated by more than one class, and we provided numerical simulations on synthetic dataset. This theoretical approach contrasts with the traditional empirical validation of biologically inspired networks and paves the way for understanding how local learning rules enable neurons to form assemblies able to represent complex concepts.
Fichier principal
Vignette du fichier
CHANI_version_finale_arxiv-2.pdf (1.34 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04589554 , version 1 (28-05-2024)

Licence

Identifiants

Citer

Sophie Jaffard, Samuel Vaiter, Patricia Reynaud-Bouret. CHANI: Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration. 2024. ⟨hal-04589554⟩
31 Consultations
27 Téléchargements

Altmetric

Partager

More