Computational Capabilities of Analog and Evolving Neural Networks over Infinite Input Streams - Université Paris Cité Accéder directement au contenu
Article Dans Une Revue Journal of Computer and System Sciences Année : 2019

Computational Capabilities of Analog and Evolving Neural Networks over Infinite Input Streams

Résumé

Analog and evolving recurrent neural networks are super-Turing powerful. Here, we consider analog and evolving neural nets over infinite input streams. We then characterize the topological complexity of their ω-languages as a function of the specific analog or evolving weights that they employ. As a consequence, two infinite hierarchies of classes of analog and evolving neural networks based on the complexity of their underlying weights can be derived. These results constitute an optimal refinement of the super-Turing expressive power of analog and evolving neural networks. They show that analog and evolving neural nets represent natural models for oracle-based infinite computation.
Fichier principal
Vignette du fichier
CabessaFinkelJCSS18.pdf (575.91 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02318257 , version 1 (16-10-2019)

Identifiants

Citer

Jérémie Cabessa, Olivier Finkel. Computational Capabilities of Analog and Evolving Neural Networks over Infinite Input Streams. Journal of Computer and System Sciences, 2019, ⟨10.1016/j.jcss.2018.11.003⟩. ⟨hal-02318257⟩
39 Consultations
90 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More