Open AccessMultiple clusters echo state network for chaotic time series prediction
Author(s) -
Qingsong Song,
Zuren Feng,
Renhou Li
Publication year - 2009
Publication title -
wuli xuebao
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.199
H-Index - 47
ISSN - 1000-3290
DOI - 10.7498/aps.58.5057
Subject(s) - echo state network , chaotic , echo (communications protocol) , series (stratigraphy) , computer science , state (computer science) , network topology , monte carlo method , artificial neural network , algorithm , scale (ratio) , time series , statistical physics , topology (electrical circuits) , recurrent neural network , artificial intelligence , physics , machine learning , mathematics , statistics , computer network , paleontology , combinatorics , biology , operating system , quantum mechanics
The chaotic time series prediction problem is considered. A novel type of cortex-like neural network model, i.e. multi-clusters echo state network model MCESN, regulated by a group of five growth-factors, is proposed. It is shown that characters of MCESN’ topology can be effectively determined by the growth-factors group; and that it is the MCESN possessing both small-world and scale-free properties of complex network that corresponds to the better prediction performance. In addition, Monte Carlo simulation experiments show that MCESN not only can be trained by easy algorithm, but also can achieve higher accuracy and less standard deviation prediction results than classical echo state networks.