The Super-Turing Computational Power of Interactive Evolving Recurrent Neural Networks
Détails
ID Serval
serval:BIB_0BB29E1F8380
Type
Actes de conférence (partie): contribution originale à la littérature scientifique, publiée à l'occasion de conférences scientifiques, dans un ouvrage de compte-rendu (proceedings), ou dans l'édition spéciale d'un journal reconnu (conference proceedings).
Collection
Publications
Institution
Titre
The Super-Turing Computational Power of Interactive Evolving Recurrent Neural Networks
Titre de la conférence
Artificial Neural Networks and Machine Learning – ICANN 2013
Editeur
Springer Berlin Heidelberg
Adresse
Sofia, Bulgaria
ISBN
978-3-642-40727-7
978-3-642-40728-4
978-3-642-40728-4
ISSN
0302-9743
1611-3349
1611-3349
Statut éditorial
Publié
Date de publication
2013
Peer-reviewed
Oui
Volume
8131
Série
Lecture Notes in Computer Science (LNCS)
Pages
58-65
Langue
anglais
Résumé
Understanding the dynamical and computational capabilities of neural models represents an issue of central importance. Here, we consider a model of first-order recurrent neural networks provided with the possibility to evolve over time and involved in a basic interactive and memory active computational paradigm. In this context, we prove that the so-called interactive evolving recurrent neural networks are computationally equivalent to interactive Turing machines with advice, hence capable of super-Turing potentialities. We further provide a precise characterisation of the ω-translations realised by these networks. Therefore, the consideration of evolving capabilities in a first-order neural model provides the potentiality to break the Turing barrier.
Mots-clé
recurrent neural networks, neural computation, interactive computation, analog computation, Turing machines with advice, super-Turing
Création de la notice
04/08/2017 8:53
Dernière modification de la notice
20/08/2019 12:33