Chargement en cours...

Interval Methods for Seeking Fixed Points of Recurrent Neural Networks

The paper describes an application of interval methods to train recurrent neural networks and investigate their behavior. The HIBA_USNE multithreaded interval solver for nonlinear systems and algorithmic differentiation using ADHC are used. Using interval methods, we can not only train the network,...

Description complète

Enregistré dans:
Détails bibliographiques
Publié dans:Computational Science – ICCS 2020
Auteurs principaux: Kubica, Bartłomiej Jacek, Hoser, Paweł, Wiliński, Artur
Format: Artigo
Langue:Inglês
Publié: 2020
Sujets:
Accès en ligne:https://ncbi.nlm.nih.gov/pmc/articles/PMC7304055/
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1007/978-3-030-50420-5_30
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!