Comments on ``Convergence Analysis of Adaptive Exponential Functional Link Network''

Ivo Bukovsky; Gejza Dohnal; Noriyasu Homma

doi:10.1109/TNNLS.2021.3123540

Comments on ``Convergence Analysis of Adaptive Exponential Functional Link Network''

Ivo Bukovsky, Gejza Dohnal, Noriyasu Homma

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

Abstract

This article is to comment on the derivation of the weight-update stability of in-parameter-linear nonlinear learning system with the gradient descent learning rule in the above article. Our comments are not to disqualify the commented article's whole contribution; however, the issues should be pointed out to avoid their proliferation.

Original language	English
Journal	IEEE Transactions on Neural Networks and Learning Systems
DOIs	https://doi.org/10.1109/TNNLS.2021.3123540
Publication status	Accepted/In press - 2021
Externally published	Yes

Keywords

Convergence analysis
Education
Eigenvalues and eigenfunctions
Europe
gradient descent
in-parameter-linear nonlinear learning system
Investment
Learning systems
Mechanical engineering
Stability criteria
weight-update stability.

ASJC Scopus subject areas

Software
Computer Science Applications
Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1109/TNNLS.2021.3123540

Cite this

@article{6c8a4af3a64f469bb80d2afb95339eac,

title = "Comments on ``Convergence Analysis of Adaptive Exponential Functional Link Network''",

abstract = "This article is to comment on the derivation of the weight-update stability of in-parameter-linear nonlinear learning system with the gradient descent learning rule in the above article. Our comments are not to disqualify the commented article's whole contribution; however, the issues should be pointed out to avoid their proliferation.",

keywords = "Convergence analysis, Education, Eigenvalues and eigenfunctions, Europe, gradient descent, in-parameter-linear nonlinear learning system, Investment, Learning systems, Mechanical engineering, Stability criteria, weight-update stability.",

author = "Ivo Bukovsky and Gejza Dohnal and Noriyasu Homma",

note = "Publisher Copyright: IEEE",

year = "2021",

doi = "10.1109/TNNLS.2021.3123540",

language = "English",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

publisher = "IEEE Computational Intelligence Society",

}

TY - JOUR

T1 - Comments on ``Convergence Analysis of Adaptive Exponential Functional Link Network''

AU - Bukovsky, Ivo

AU - Dohnal, Gejza

AU - Homma, Noriyasu

N1 - Publisher Copyright: IEEE

PY - 2021

Y1 - 2021

N2 - This article is to comment on the derivation of the weight-update stability of in-parameter-linear nonlinear learning system with the gradient descent learning rule in the above article. Our comments are not to disqualify the commented article's whole contribution; however, the issues should be pointed out to avoid their proliferation.

AB - This article is to comment on the derivation of the weight-update stability of in-parameter-linear nonlinear learning system with the gradient descent learning rule in the above article. Our comments are not to disqualify the commented article's whole contribution; however, the issues should be pointed out to avoid their proliferation.

KW - Convergence analysis

KW - Education

KW - Eigenvalues and eigenfunctions

KW - Europe

KW - gradient descent

KW - in-parameter-linear nonlinear learning system

KW - Investment

KW - Learning systems

KW - Mechanical engineering

KW - Stability criteria

KW - weight-update stability.

UR - http://www.scopus.com/inward/record.url?scp=85119415144&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85119415144&partnerID=8YFLogxK

U2 - 10.1109/TNNLS.2021.3123540

DO - 10.1109/TNNLS.2021.3123540

M3 - Article

AN - SCOPUS:85119415144

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

ER -

Comments on ``Convergence Analysis of Adaptive Exponential Functional Link Network''

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this