Performance evaluation of new echo state networks based on complex network

Recently, echo state networks （ESN） have aroused a lot of interest in their nonlinear dynamic system modeling capabilities. In a classical ESN, its dynamic reservoir （DR） has a sparse and random topology, but the performance of ESN with its DR taking another kind of topology is still unknown. So bas...

Full description

Saved in:
Bibliographic Details
Published inJournal of China universities of posts and telecommunications Vol. 19; no. 1; pp. 87 - 93
Main Authors LIU, Xiang, CUI, Hong-yan, ZHOU, Tian-jun, CHEN, Jian-ya
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 01.02.2012
Key Laboratory of Network System Architecture and Convergence, Beijing University of Posts and Telecommunications, Beijing 100876, China
Subjects
complex network
Dynamical systems
ESN
Networks
Nonlinear dynamics
Scanning tunneling microscopy
short-term memory capacity
Simulation
Spectra
Time series
time series prediction
Topology
回声
复杂网络理论
建模能力
性能评价
拓扑结构
时间序列分析
状态
非线性动态系统
complex network
ESN
time series prediction
short-term memory capacity
Online AccessGet full text

Cover

More Information
Summary:Recently, echo state networks （ESN） have aroused a lot of interest in their nonlinear dynamic system modeling capabilities. In a classical ESN, its dynamic reservoir （DR） has a sparse and random topology, but the performance of ESN with its DR taking another kind of topology is still unknown. So based on complex network theory, three new ESNs are proposed and investigated in this paper. The small-world topology, scale-free topology and the mixed topology of small-world effect and scale-free feature are considered in these new ESNs. We studied the relationship between DR architecture and prediction capability. In our simulation experiments, we used two widely used time series to test the prediction performance among the new ESNs and classical ESN, and used the independent identically distributed （i.i.d） time series to analyze the short-term memory （STM） capability. We answer the following questions： What are the differences of these ESNs in the prediction performance？ Can the spectral radius of the internal weights matrix be wider？ What is the short-term memory capability？ The experimental results show that the proposed new ESNs have better prediction performance, wider spectral radius and almost the same STM capacity as classical ESN＇s.
Bibliography:ESN, complex network, time series prediction, short-term memory capacity
11-3486/TN
Recently, echo state networks （ESN） have aroused a lot of interest in their nonlinear dynamic system modeling capabilities. In a classical ESN, its dynamic reservoir （DR） has a sparse and random topology, but the performance of ESN with its DR taking another kind of topology is still unknown. So based on complex network theory, three new ESNs are proposed and investigated in this paper. The small-world topology, scale-free topology and the mixed topology of small-world effect and scale-free feature are considered in these new ESNs. We studied the relationship between DR architecture and prediction capability. In our simulation experiments, we used two widely used time series to test the prediction performance among the new ESNs and classical ESN, and used the independent identically distributed （i.i.d） time series to analyze the short-term memory （STM） capability. We answer the following questions： What are the differences of these ESNs in the prediction performance？ Can the spectral radius of the internal weights matrix be wider？ What is the short-term memory capability？ The experimental results show that the proposed new ESNs have better prediction performance, wider spectral radius and almost the same STM capacity as classical ESN＇s.
ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:1005-8885
DOI:10.1016/S1005-8885(11)60232-X