Provable local learning rule by expert aggregation for a Hawkes network - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2023

Provable local learning rule by expert aggregation for a Hawkes network

Résumé

We propose a simple network of Hawkes processes as a cognitive model capable of learning to classify objects. Our learning algorithm, named EWAK for Exponentially Weighted Average and Kalikow decomposition, is based on a local synaptic learning rule based on firing rates at each output node. We were able to use local regret bounds to prove mathematically that the network is able to learn on average and even asymptotically under more restrictive assumptions.
Fichier principal
Vignette du fichier
qprqrfwynqgnqqbnqgcrztdschtnsfzc.pdf (1003.75 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04065229 , version 1 (12-04-2023)
hal-04065229 , version 2 (21-02-2024)

Identifiants

Citer

Sophie Jaffard, Samuel Vaiter, Alexandre Muzy, Patricia Reynaud-Bouret. Provable local learning rule by expert aggregation for a Hawkes network. 2023. ⟨hal-04065229v1⟩
206 Consultations
89 Téléchargements

Altmetric

Partager

More