.png){kind=icon}
返回
Training Echo State Networks with Regularization Through Dimensionality Reduction
.png){kind=icon}
PRE
AI
DOI：10.1007/s12559-017-9450-z.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we introduce a new framework to train a class of recurrent neural network, called Echo State Network, to predict real valued time-series and to provide a visualization of the modeled system dynamics. The method consists in projecting the output of the internal layer of the network on a lower dimensional space, before training the output layer to learn the target task. Notably, we enforce a regularization constraint that leads to better generalization capabilities. We evaluate the performances of our approach on several benchmark tests, using different techniques to train the readout of the network, achieving superior predictive performance when using the proposed framework. Finally, we provide an insight on the effectiveness of the implemented mechanics through a visualization of the trajectory in the phase space and relying on the methodologies of nonlinear time-series analysis. By applying our method on well-known chaotic systems, we provide evidence that the lower dimensional embedding retains the dynamical properties of the underlying system better than the full-dimensional internal states of the network.
Keyword:
Echo state network
Nonlinear time-series analysis
Dimensionality reduction
Time-series prediction
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.3
论文数:
1.6K
被引数:
3.6K
机构
引用论文
Two Electrolyte Decomposition Pathways at NMC Electrodes in Lithium-Ion Batteries锂离子电池中NMC电极的两种电解质分解途径
PREAI
分享收藏Short-term electric load and temperature forecasting using wavelet echo state networks with neural reconstruction.png)
ENERGY
ENERGYIF9.4
PREAI
分享收藏An online generalized eigenvalue version of Laplacian Eigenmaps for visual big dataNEUROCOMPUTING
OAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏
查看更多内容