Universal approximation property of stochastic configuration networks for time series

Universal approximation property of stochastic configuration networks for time series

Abstract For the purpose of processing sequential data, such as time series, and addressing the challenge of manually tuning the architecture of traditional recurrent neural networks (RNNs), this paper introduces a novel approach-the Recurrent Stochastic Configuration Network (RSCN). This network is...

Descripció completa

Dades bibliogràfiques
Autors principals: Jin-Xi Zhang, Hangyi Zhao, Xuefeng Zhang
Format: Article
Idioma:English
Publicat: Springer 2024-03-01
Col·lecció:Industrial Artificial Intelligence
Matèries:
Recurrent neural networks
Stochastic configuration networks
Incremental learning
Time series
Deep learning
Accés en línia:https://doi.org/10.1007/s44244-024-00017-7

Internet

https://doi.org/10.1007/s44244-024-00017-7

Ítems similars