Table des matières: :: Library Catalog

Image de couverture de livre

Enregistré dans:

Détails bibliographiques
Auteur principal:	Frimane, Âzeddine
Format:	Recurso digital
Langue:	anglais
Publié:	Zenodo 2026
Sujets:	linear attention, Dirichlet process, Bayesian nonparametrics, recurrent neural networks, state space models, exponential smoothing, hierarchical Dirichlet process, sequence modeling
Accès en ligne:	https://doi.org/10.5281/zenodo.18975350
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Table des matières:

<p>This paper shows that the recurrent update used in linear attention models is mathematically equivalent to Bayesian inference under a Dependent Dirichlet Process. The forgetting rate, the input-dependent gate, and the multi-head structure each receive a clean probabilistic interpretation. The result is exact and holds by construction, not as an approximation.</p>