Configuring RBF neural networks

I. Sohn; N. Ansari

doi:10.1049/el:19980469

Configuring RBF neural networks

I. Sohn, N. Ansari

Electrical and Computer Engineering

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

11 Scopus citations

Abstract

A novel method (based on the characteristics of scatter matrices and frequency-sensitive competitive learning) for training the hidden layer of a radial basis function neural network is proposed. The method is demonstrated to be robust and to outperform the state-of-the-art algorithm.

Original language	English (US)
Pages (from-to)	684-685
Number of pages	2
Journal	Electronics Letters
Volume	34
Issue number	7
DOIs	https://doi.org/10.1049/el:19980469
State	Published - Apr 2 1998

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering

Access to Document

10.1049/el:19980469

Cite this

@article{c0117058ab294094885166b1ad7390d1,

title = "Configuring RBF neural networks",

abstract = "A novel method (based on the characteristics of scatter matrices and frequency-sensitive competitive learning) for training the hidden layer of a radial basis function neural network is proposed. The method is demonstrated to be robust and to outperform the state-of-the-art algorithm.",

author = "I. Sohn and N. Ansari",

year = "1998",

month = apr,

day = "2",

doi = "10.1049/el:19980469",

language = "English (US)",

volume = "34",

pages = "684--685",

journal = "Electronics Letters",

issn = "0013-5194",

publisher = "Institution of Engineering and Technology",

number = "7",

}

TY - JOUR

T1 - Configuring RBF neural networks

AU - Sohn, I.

AU - Ansari, N.

PY - 1998/4/2

Y1 - 1998/4/2

N2 - A novel method (based on the characteristics of scatter matrices and frequency-sensitive competitive learning) for training the hidden layer of a radial basis function neural network is proposed. The method is demonstrated to be robust and to outperform the state-of-the-art algorithm.

AB - A novel method (based on the characteristics of scatter matrices and frequency-sensitive competitive learning) for training the hidden layer of a radial basis function neural network is proposed. The method is demonstrated to be robust and to outperform the state-of-the-art algorithm.

UR - http://www.scopus.com/inward/record.url?scp=0032473640&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032473640&partnerID=8YFLogxK

U2 - 10.1049/el:19980469

DO - 10.1049/el:19980469

M3 - Article

AN - SCOPUS:0032473640

SN - 0013-5194

VL - 34

SP - 684

EP - 685

JO - Electronics Letters

JF - Electronics Letters

IS - 7

ER -

Configuring RBF neural networks

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this