Please submit manuscripts in either of the following two submission systems

    ScholarOne Manuscripts

  • ScholarOne

    • 勤云稿件系统

  • 登录

Search by Issue

  • 2024 Vol.31
  • 2023 Vol.30
  • 2022 Vol.29
  • 2021 Vol.28
  • 2020 Vol.27
  • 2019 Vol.26
  • 2018 Vol.25
  • 2017 Vol.24
  • 2016 vol.23
  • 2015 vol.22
  • 2014 vol.21
  • 2013 vol.20
  • 2012 vol.19
  • 2011 vol.18
  • 2010 vol.17
  • 2009 vol.16
  • No.1
  • No.2

Search by Keywords

  • Search by Title
  • Search by Keywords
  • Search by Abstract
  • Search by Author's Chinese Name
  • Search by Author's English Name
  • Search by Fund

News & AnnouncementMORE

Supervised by Ministry of Industry and Information Technology of The People's Republic of China Sponsored by Harbin Institute of Technology Editor-in-chief Yu Zhou ISSNISSN 1005-9113 CNCN 23-1378/T

期刊网站二维码
微信公众号二维码
Related citation:Yingchun Bo,Xin Zhang.Investigation on Dynamics of Echo State Networks[J].Journal of Harbin Institute Of Technology(New Series),2023,30(4):25-36.DOI:10.11916/j.issn.1005-9113.2022003.
【Print】   【HTML】   【PDF download】   【View/Add Comment】  【Download reader】  【 Close 】
←Previous|Next→ Back Issue    Advanced Search
This paper has been: browsed 477times   downloaded 540times 本文二维码信息
码上扫一扫！
Shared by: Wechat More
Font:larger+|default|smaller-
Investigation on Dynamics of Echo State Networks
Author NameAffiliation
Yingchun Bo College of Control Science and Engineering, China University of Petroleum, Qingdao 266580, Shandong, China 
Xin Zhang College of Control Science and Engineering, China University of Petroleum, Qingdao 266580, Shandong, China 
Abstract:
Dynamics is a key issue about understanding recurrent neural networks (RNNs). Because of the complexity, the problem still remains unanswered in spite of many important progresses. Echo state network (ESN) is a simple approach to design RNNs. It is possible to investigate ESNs’ dynamics deeply. However, most of dynamic studies have mainly concentrated on the shallow ESNs and seldom of them explain the dynamics of the deep ones. Therefore, this paper investigates the dynamics of four typical ESNs under a unified theoretical framework. These ESNs contain both the shallow versions and the deep ones. This investigation is helpful to clarify the dynamics of ESNs in a general sense. Also, the short-term memory (STM) of different ESNs is analyzed, which is closely related to the dynamics. This analysis is helpful to determine the hyper-parameters of ESNs for given problems. In addition, the problem-solving abilities of ESNs are investigated through modeling two time series tasks. It further explains the influence of the dynamics on ESN’s performance.
Key words:  recurrent neural networks  reservoir computing  memory  dynamics
DOI：10.11916/j.issn.1005-9113.2022003
Clc Number:TP183
Fund:

LINKS

Copyright © The Editorial Department of Journal of Harbin Institute of Technology
Address: 92 West Dazhi Street, Nan Gang District, Harbin, Heilongjiang Province, China Postcode: 150001
(C)2015 JOURNAL OF HIT ALL RIGHTS RESERVED. ICP. 0000423255