Adaptive on-line ANN learning algorithm and application to identification of non-linear systems

Daohang Sha; Vladimir B. Bajić

Adaptive on-line ANN learning algorithm and application to identification of non-linear systems

Daohang Sha, Vladimir B. Bajić

Research output: Contribution to journal › Article › peer-review

Abstract

A new on-line adaptive learning rate algorithm for I/O identification based on two ANNs is proposed. The algorithm is derived from the convergence analysis of the conventional gradient descent method. Simulation experiments are given to illustrate the advantages of the proposed algorithm in its application to an identification problem of some non-linear dynamic systems.

Original language	English (US)
Pages (from-to)	521-529
Number of pages	9
Journal	Informatica (Ljubljana)
Volume	23
Issue number	4
State	Published - Dec 1999
Externally published	Yes

ASJC Scopus subject areas

Software
Theoretical Computer Science
Computer Science Applications
Artificial Intelligence

Cite this

@article{4199543bf45f480e95267ae06ee2b7e6,

title = "Adaptive on-line ANN learning algorithm and application to identification of non-linear systems",

abstract = "A new on-line adaptive learning rate algorithm for I/O identification based on two ANNs is proposed. The algorithm is derived from the convergence analysis of the conventional gradient descent method. Simulation experiments are given to illustrate the advantages of the proposed algorithm in its application to an identification problem of some non-linear dynamic systems.",

author = "Daohang Sha and Baji{\'c}, {Vladimir B.}",

year = "1999",

month = dec,

language = "English (US)",

volume = "23",

pages = "521--529",

journal = "Informatica (Ljubljana)",

issn = "0350-5596",

publisher = "Slovene Society Informatika",

number = "4",

}

TY - JOUR

T1 - Adaptive on-line ANN learning algorithm and application to identification of non-linear systems

AU - Sha, Daohang

AU - Bajić, Vladimir B.

PY - 1999/12

Y1 - 1999/12

N2 - A new on-line adaptive learning rate algorithm for I/O identification based on two ANNs is proposed. The algorithm is derived from the convergence analysis of the conventional gradient descent method. Simulation experiments are given to illustrate the advantages of the proposed algorithm in its application to an identification problem of some non-linear dynamic systems.

AB - A new on-line adaptive learning rate algorithm for I/O identification based on two ANNs is proposed. The algorithm is derived from the convergence analysis of the conventional gradient descent method. Simulation experiments are given to illustrate the advantages of the proposed algorithm in its application to an identification problem of some non-linear dynamic systems.

UR - http://www.scopus.com/inward/record.url?scp=0033337637&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0033337637

SN - 0350-5596

VL - 23

SP - 521

EP - 529

JO - Informatica (Ljubljana)

JF - Informatica (Ljubljana)

IS - 4

ER -

Adaptive on-line ANN learning algorithm and application to identification of non-linear systems

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this