arrow
返回

Reservoir computing dissection and visualization based on directed network embedding

delete2021-07-01
delete5
PRE
AI
X
Xinyu Han
Y
Yi Zhao *
DOI:10.1016/j.neucom.2021.02.029delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
The reservoir computing (RC) has recently gained considerable attention in practice and many methods have been developed to study its internal mechanism. However, the specific role played by the reservoir nodes of RC in time series prediction is still to be defined. An interpretable RC model wherein its reservoir network is designated as the directed acyclic network (DAN) is proposed with focus on time series prediction in this paper. In virtue of asymmetric transitivity and hierarchical structure of DAN, we present a directed network embedding method to identify the latent memory property of each node in the DAN. Such memory property is utilized to characterize the roles played by the reservoir nodes on the prediction performance of the RC. Meanwhile, it can also be leveraged to identify the corresponding memory community of DAN. As a result, we demonstrate how the reservoir network structure takes effect on the prediction performance from the perspective of memory community. In addition, two novel hyperparameters with the deterministic meaning are introduced to quantify the influence of the model initialization on the reservoir input so as to facilitate further dissection of the interpretable RC. The experimental results indicate that tuning these hyperparameters, which is explicable in terms of the Taylor expansion of the activation function, serves as an essential step in achieving superior prediction performance. Finally, comparative experiments with some other RC models on various time series benchmarks are also conducted. (c) 2021 Elsevier B.V. All rights reserved.
Keyword:
Reservoir computing
Directed network embedding
Memory community structure
Time series prediction
AI总结

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

Neurocomputing 封面图
Neurocomputing
IF:
6.5
论文数:
2.5W
被引数:
6.5W

机构

H
harbin institute of technology
学者数:
8.0W
论文数: 6.6W
被引数: 66
引用论文

引用论文

Growing Echo-State Network With Multiple Subreservoirs
err2017-02-01
err141
PREAI
errQiao, Junfei; Li, Fanjun; Han, Honggui; Li, Wenjing
err分享
err收藏
err分享
err收藏
Assessment of animal welfare for helicopter shooting of feral horses
err2017-01-01
err0
PREAI
errJordan O. Hampton; Glenn P. Edwards; Brendan D. Cowled; David M. Forsyth; Timothy H. Hyndman; Andrew L. Perry; Corissa J. Miller; Peter J. Adams; Teresa Collins
err分享
err收藏
Deep reservoir computing: A critical experimental analysis
err2017-12-01
err327
errOAAI
errGallicchio, Claudio; Micheli, Alessio; Pedrelli, Luca
err分享
err收藏
Computational analysis of memory capacity in echo state networks
err2016-11-01
err57
PREAI
errFarkas, Igor; Bosak, Radomir; Gergel, Peter
err分享
err收藏
学者 查看更多内容