.png){kind=icon}
返回
An Online Learning Strategy for Echo State Network
.png){kind=icon}
PRE
AI
DOI：10.1109/TSMC.2023.3319357.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As an effective alternative to recurrent neural networks, the echo state network (ESN) has achieved great success. However, the commonly-used batch learning-based algorithms prevent the ESN from being able to learn and train online. In this article, inspired by the Woodbury matrix identity, an online learning ESN named Woodbury online learning ESN (WOLESN) is proposed, which allows new data to arrive in a one-by-one or block-by-block manner. Experiments on the benchmark datasets of time series prediction and comparison models verify the effectiveness and superiority of the WOLESN. In addition, observing the relationship between the time series prediction and robot control, experiments on the redundant manipulator are designed with the aid of the proposed WOLESN, of which results indicate that the WOLESN does an excellent job of predicting the trajectory of the robot with tiny errors. The code of WOLESN is publicly available at https://github.com/LongJin-lab/the-supplementary-file-for-WOLESN.
Keyword:
Reservoirs
Manipulators
Task analysis
Time series analysis
Neurons
Sparse matrices
Predictive models
RNN
time series prediction
woodbury online learning echo state network (WOLESN)
期刊
IF:
10.5
论文数:
1.1W
被引数:
5.0W
机构
引用论文
.png){kind=icon}
分享收藏
Echo State Network-Based Decentralized Control of Continuous-Time Nonlinear Large-Scale Interconnected Systems基于回声状态网络的连续时间非线性大型互联系统分散控制
PREAI
分享收藏
查看更多内容