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...

Cur síos iomlán

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí: Jin-Xi Zhang, Hangyi Zhao, Xuefeng Zhang
Formáid: Alt
Teanga:English
Foilsithe / Cruthaithe: Springer 2024-03-01
Sraith:Industrial Artificial Intelligence
Ábhair:
Recurrent neural networks
Stochastic configuration networks
Incremental learning
Time series
Deep learning
Rochtain ar líne:https://doi.org/10.1007/s44244-024-00017-7

Ar líne

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

Míreanna comhchosúla