A Backward Learning Algorithm in Polynomial Echo State Networks

Cuili Yang; Xinxin Zhu; Junfei Qiao

Machine Learning and Intelligent Communications. 4th International Conference, MLICOM 2019, Nanjing, China, August 24–25, 2019, Proceedings

Research Article

A Backward Learning Algorithm in Polynomial Echo State Networks

Download

45 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-030-32388-2_43,
    author={Cuili Yang and Xinxin Zhu and Junfei Qiao},
    title={A Backward Learning Algorithm in Polynomial Echo State Networks},
    proceedings={Machine Learning and Intelligent Communications. 4th International Conference, MLICOM 2019, Nanjing, China, August 24--25, 2019, Proceedings},
    proceedings_a={MLICOM},
    year={2019},
    month={10},
    keywords={Polynomial echo state network Subset selection Backward learning algorithm},
    doi={10.1007/978-3-030-32388-2_43}
}

Cuili Yang
Xinxin Zhu
Junfei Qiao
Year: 2019
A Backward Learning Algorithm in Polynomial Echo State Networks
MLICOM
Springer
DOI: 10.1007/978-3-030-32388-2_43

Cuili Yang¹^,*, Xinxin Zhu¹^,*, Junfei Qiao¹^,*

1: Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligence System

*Contact email: clyang5@bjut.edu.cn, 1205580412@qq.com, junfeiq@bjut.edu.cn

Abstract

Recently, the polynomial echo state network (PESN) has been proposed to incorporate the high order information of input features. However, there are some redundant inputs in PESN, which results in high computational cost. To solve this problem, a backward learning algorithm is designed for PESN, which is denoted as BL-PESN for short. The criterion for input features removing is designed to prune the insignificant input features one by one. The simulation results illustrate that the proposed approach has better prediction accuracy and less testing time than other ESNs.

Keywords: Polynomial echo state network Subset selection Backward learning algorithm

Published: 2019-10-28
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-030-32388-2_43