.png){kind=icon}
返回
Multi-module echo state network with variable skip length for chaotic time series prediction
.png){kind=icon}
PRE
AI
DOI：10.1016/j.asoc.2024.112441.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Echo state networks (ESNs) have been extensively applied in time series prediction problems. However, the memory-nonlinearity trade-off problem severely limits the ability of ESNs to deal with chaotic time series prediction problems. In this study, a multi-module echo state network with variable skip length (MESN-VSL) is proposed to address this problem. First, the reservoir is divided into a nonlinear mapping module and multiple linear memory modules based on the idea of memory and nonlinearity separation. This idea can effectively balance the memory-nonlinearity trade-off problems. Second, a multi-module mechanism with skip length is put forward to model the characteristics of chaotic time series. The skip length and the number of linear memory modules of the MESN-VSL model are automatically determined based on the idea of phase-space reconstruction. Finally, the experimental results further demonstrate that the MESN-VSL model is superior to some existing models in chaotic time series prediction.
Keyword:
Memory capacity
Nonlinear mapping
Echo state networks
Chaotic time series prediction
期刊
IF:
6.6
论文数:
1.4W
被引数:
4.8W
机构
引用论文
Predicting chaotic time series and replicating chaotic attractors based on two novel echo state network models.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
Bimodal distributions of seedling weight in relation to density of Festuca paradoxa Desv.Nature
NatureIF0
PREAI
分享收藏分享收藏
查看更多内容