Online learning of windmill time series using Long Short-term Cognitive Networks
作者：
Highlights：
• Traditional recurrent neural networks are often expensive to use in online settings.
• Long Short-term Cognitive Neural Networks seem promising for online learning.
• Neural blocks of this network process a batch of available data in online settings.
• Forecasting errors are smaller than those of state-of-the-art neural systems.
• The learning algorithm within each neural block makes the network much faster.
摘要
•Traditional recurrent neural networks are often expensive to use in online settings.•Long Short-term Cognitive Neural Networks seem promising for online learning.•Neural blocks of this network process a batch of available data in online settings.•Forecasting errors are smaller than those of state-of-the-art neural systems.•The learning algorithm within each neural block makes the network much faster.
论文关键词：Long Short-term Cognitive Network,Recurrent Neural Network,Multivariate time series,Forecasting
论文评审过程：Received 10 July 2021, Revised 25 May 2022, Accepted 31 May 2022, Available online 6 June 2022, Version of Record 14 June 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117721
