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...

Disgrifiad llawn

Manylion Llyfryddiaeth
Prif Awduron: Jin-Xi Zhang, Hangyi Zhao, Xuefeng Zhang
Fformat: Erthygl
Iaith:English
Cyhoeddwyd: Springer 2024-03-01
Cyfres:Industrial Artificial Intelligence
Pynciau:
Mynediad Ar-lein:https://doi.org/10.1007/s44244-024-00017-7

Eitemau Tebyg