Evolutionary radial basis function networks

Seyedali Mirjalili

doi:10.1007/978-3-319-93025-1_8

Evolutionary radial basis function networks

Seyedali Mirjalili

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

18 Citations (Scopus)

Abstract

Radial Basis Function (RBF) networks are one of the most popular and applied type of neural networks. RBF networks are universal approximators and considered as special form of multilayer feedforward neural networks that contain only one hidden layer with Gaussian based activation functions. This chapter trains such NNs with several optimisation algorithms and compares their performance.

Original language	English
Title of host publication	Studies in Computational Intelligence
Publisher	Springer Verlag
Pages	105-139
Number of pages	35
DOIs	https://doi.org/10.1007/978-3-319-93025-1_8
Publication status	Published - 1 Jan 2019
Externally published	Yes

Publication series

Name	Studies in Computational Intelligence
Volume	780
ISSN (Print)	1860-949X

Access to Document

10.1007/978-3-319-93025-1_8

Cite this

@inbook{394b1333492c45669443f1a5eb86a80c,

title = "Evolutionary radial basis function networks",

abstract = "Radial Basis Function (RBF) networks are one of the most popular and applied type of neural networks. RBF networks are universal approximators and considered as special form of multilayer feedforward neural networks that contain only one hidden layer with Gaussian based activation functions. This chapter trains such NNs with several optimisation algorithms and compares their performance.",

author = "Seyedali Mirjalili",

year = "2019",

month = jan,

day = "1",

doi = "10.1007/978-3-319-93025-1_8",

language = "English",

series = "Studies in Computational Intelligence",

publisher = "Springer Verlag",

pages = "105--139",

booktitle = "Studies in Computational Intelligence",

}

TY - CHAP

T1 - Evolutionary radial basis function networks

AU - Mirjalili, Seyedali

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Radial Basis Function (RBF) networks are one of the most popular and applied type of neural networks. RBF networks are universal approximators and considered as special form of multilayer feedforward neural networks that contain only one hidden layer with Gaussian based activation functions. This chapter trains such NNs with several optimisation algorithms and compares their performance.

AB - Radial Basis Function (RBF) networks are one of the most popular and applied type of neural networks. RBF networks are universal approximators and considered as special form of multilayer feedforward neural networks that contain only one hidden layer with Gaussian based activation functions. This chapter trains such NNs with several optimisation algorithms and compares their performance.

UR - http://www.scopus.com/inward/record.url?scp=85049373518&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-93025-1_8

DO - 10.1007/978-3-319-93025-1_8

M3 - Chapter

AN - SCOPUS:85049373518

T3 - Studies in Computational Intelligence

SP - 105

EP - 139

BT - Studies in Computational Intelligence

PB - Springer Verlag

ER -

Evolutionary radial basis function networks

Abstract

Publication series

Access to Document

Other files and links

Fingerprint

Cite this