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,...

Descripción completa

Detalles Bibliográficos
Autores principales: Kubica, Bartłomiej Jacek, Hoser, Paweł, Wiliński, Artur
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7304055/
http://dx.doi.org/10.1007/978-3-030-50420-5_30
_version_ 1783548188846718976
author Kubica, Bartłomiej Jacek
Hoser, Paweł
Wiliński, Artur
author_facet Kubica, Bartłomiej Jacek
Hoser, Paweł
Wiliński, Artur
author_sort Kubica, Bartłomiej Jacek
collection PubMed
description 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, but precisely localize all stationary points of the network. Preliminary numerical results for continuous Hopfield-like networks are presented.
format Online
Article
Text
id pubmed-7304055
institution National Center for Biotechnology Information
language English
publishDate 2020
record_format MEDLINE/PubMed
spelling pubmed-73040552020-06-19 Interval Methods for Seeking Fixed Points of Recurrent Neural Networks Kubica, Bartłomiej Jacek Hoser, Paweł Wiliński, Artur Computational Science – ICCS 2020 Article 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, but precisely localize all stationary points of the network. Preliminary numerical results for continuous Hopfield-like networks are presented. 2020-05-22 /pmc/articles/PMC7304055/ http://dx.doi.org/10.1007/978-3-030-50420-5_30 Text en © Springer Nature Switzerland AG 2020 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Article
Kubica, Bartłomiej Jacek
Hoser, Paweł
Wiliński, Artur
Interval Methods for Seeking Fixed Points of Recurrent Neural Networks
title Interval Methods for Seeking Fixed Points of Recurrent Neural Networks
title_full Interval Methods for Seeking Fixed Points of Recurrent Neural Networks
title_fullStr Interval Methods for Seeking Fixed Points of Recurrent Neural Networks
title_full_unstemmed Interval Methods for Seeking Fixed Points of Recurrent Neural Networks
title_short Interval Methods for Seeking Fixed Points of Recurrent Neural Networks
title_sort interval methods for seeking fixed points of recurrent neural networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7304055/
http://dx.doi.org/10.1007/978-3-030-50420-5_30
work_keys_str_mv AT kubicabartłomiejjacek intervalmethodsforseekingfixedpointsofrecurrentneuralnetworks
AT hoserpaweł intervalmethodsforseekingfixedpointsofrecurrentneuralnetworks
AT wilinskiartur intervalmethodsforseekingfixedpointsofrecurrentneuralnetworks

Ejemplares similares