A dynamic parzen window approach based on error-entropy minimization algorithm for supervised training of nonlinear adaptive system

Zibin Wang; Xuemei Ren; Yan Liu

doi:10.1109/CHICC.2006.4347162

A dynamic parzen window approach based on error-entropy minimization algorithm for supervised training of nonlinear adaptive system

Zibin Wang^*, Xuemei Ren, Yan Liu

^*Corresponding author for this work

School of Automation

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper presents a dynamic Parzen window estimator in the MEE approach for supervised training of nonlinear adaptive system. By adjusting the Parzen window width dynamically so that the overall information force (OIF) among error-samples of each step is as large as possible, the training speed is accelerated and the error is reduced. The simulation result has proved the effectiveness and robustness of this algorithm.

Original language	English
Title of host publication	Proceedings of the 26th Chinese Control Conference, CCC 2007
Pages	222-226
Number of pages	5
DOIs	https://doi.org/10.1109/CHICC.2006.4347162
Publication status	Published - 2007
Event	26th Chinese Control Conference, CCC 2007 - Zhangjiajie, China Duration: 26 Jul 2007 → 31 Jul 2007

Publication series

Name	Proceedings of the 26th Chinese Control Conference, CCC 2007

Conference

Conference	26th Chinese Control Conference, CCC 2007
Country/Territory	China
City	Zhangjiajie
Period	26/07/07 → 31/07/07

Keywords

Dynamic parzen window approach
Error-entropy minimization (MEE)
Information Theoretic Learning (ITL)

Access to Document

10.1109/CHICC.2006.4347162

Cite this

Wang, Z., Ren, X., & Liu, Y. (2007). A dynamic parzen window approach based on error-entropy minimization algorithm for supervised training of nonlinear adaptive system. In Proceedings of the 26th Chinese Control Conference, CCC 2007 (pp. 222-226). Article 4347162 (Proceedings of the 26th Chinese Control Conference, CCC 2007). https://doi.org/10.1109/CHICC.2006.4347162

@inproceedings{ae62a5d39586420090d163a1039fd505,

title = "A dynamic parzen window approach based on error-entropy minimization algorithm for supervised training of nonlinear adaptive system",

abstract = "This paper presents a dynamic Parzen window estimator in the MEE approach for supervised training of nonlinear adaptive system. By adjusting the Parzen window width dynamically so that the overall information force (OIF) among error-samples of each step is as large as possible, the training speed is accelerated and the error is reduced. The simulation result has proved the effectiveness and robustness of this algorithm.",

keywords = "Dynamic parzen window approach, Error-entropy minimization (MEE), Information Theoretic Learning (ITL)",

author = "Zibin Wang and Xuemei Ren and Yan Liu",

year = "2007",

doi = "10.1109/CHICC.2006.4347162",

language = "English",

isbn = "7900719229",

series = "Proceedings of the 26th Chinese Control Conference, CCC 2007",

pages = "222--226",

booktitle = "Proceedings of the 26th Chinese Control Conference, CCC 2007",

note = "26th Chinese Control Conference, CCC 2007 ; Conference date: 26-07-2007 Through 31-07-2007",

}

Wang, Z, Ren, X & Liu, Y 2007, A dynamic parzen window approach based on error-entropy minimization algorithm for supervised training of nonlinear adaptive system. in Proceedings of the 26th Chinese Control Conference, CCC 2007., 4347162, Proceedings of the 26th Chinese Control Conference, CCC 2007, pp. 222-226, 26th Chinese Control Conference, CCC 2007, Zhangjiajie, China, 26/07/07. https://doi.org/10.1109/CHICC.2006.4347162

A dynamic parzen window approach based on error-entropy minimization algorithm for supervised training of nonlinear adaptive system. / Wang, Zibin; Ren, Xuemei; Liu, Yan.
Proceedings of the 26th Chinese Control Conference, CCC 2007. 2007. p. 222-226 4347162 (Proceedings of the 26th Chinese Control Conference, CCC 2007).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A dynamic parzen window approach based on error-entropy minimization algorithm for supervised training of nonlinear adaptive system

AU - Wang, Zibin

AU - Ren, Xuemei

AU - Liu, Yan

PY - 2007

Y1 - 2007

N2 - This paper presents a dynamic Parzen window estimator in the MEE approach for supervised training of nonlinear adaptive system. By adjusting the Parzen window width dynamically so that the overall information force (OIF) among error-samples of each step is as large as possible, the training speed is accelerated and the error is reduced. The simulation result has proved the effectiveness and robustness of this algorithm.

AB - This paper presents a dynamic Parzen window estimator in the MEE approach for supervised training of nonlinear adaptive system. By adjusting the Parzen window width dynamically so that the overall information force (OIF) among error-samples of each step is as large as possible, the training speed is accelerated and the error is reduced. The simulation result has proved the effectiveness and robustness of this algorithm.

KW - Dynamic parzen window approach

KW - Error-entropy minimization (MEE)

KW - Information Theoretic Learning (ITL)

UR - http://www.scopus.com/inward/record.url?scp=37749046264&partnerID=8YFLogxK

U2 - 10.1109/CHICC.2006.4347162

DO - 10.1109/CHICC.2006.4347162

M3 - Conference contribution

AN - SCOPUS:37749046264

SN - 7900719229

SN - 9787900719225

T3 - Proceedings of the 26th Chinese Control Conference, CCC 2007

SP - 222

EP - 226

BT - Proceedings of the 26th Chinese Control Conference, CCC 2007

T2 - 26th Chinese Control Conference, CCC 2007

Y2 - 26 July 2007 through 31 July 2007

ER -

A dynamic parzen window approach based on error-entropy minimization algorithm for supervised training of nonlinear adaptive system

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this