On the Kolmogorov neural networks

Aysu Ismayilova; Vugar E. Ismailov

doi:10.1016/j.neunet.2024.106333

On the Kolmogorov neural networks

Aysu Ismayilova, Vugar E. Ismailov^*

^*Corresponding author for this work

Khazar University

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

Abstract

In this paper, we show that the Kolmogorov two hidden layer neural network model with a continuous, discontinuous bounded and unbounded activation function in the second hidden layer can precisely represent continuous, discontinuous bounded and all unbounded multivariate functions, respectively.

Original language	English
Article number	106333
Pages (from-to)	1-6
Number of pages	6
Journal	Neural Networks
Volume	176
Early online date	22 Apr 2024
DOIs	https://doi.org/10.1016/j.neunet.2024.106333
Publication status	Published - Aug 2024

Bibliographical note

Publisher Copyright:
© 2024 Elsevier Ltd

Keywords

Conjugate operator
Dual space
Indicator function
Kolmogorov's superposition theorem
Linear functional
Lipschitz function

Access to Document

10.1016/j.neunet.2024.106333

1-s2.0-S0893608024002570-mainFinal published version, 720 KBLicence: Taverne

Cite this

@article{cf0ae4e823d446aca88b431f863e54d2,

title = "On the Kolmogorov neural networks",

abstract = "In this paper, we show that the Kolmogorov two hidden layer neural network model with a continuous, discontinuous bounded and unbounded activation function in the second hidden layer can precisely represent continuous, discontinuous bounded and all unbounded multivariate functions, respectively.",

keywords = "Conjugate operator, Dual space, Indicator function, Kolmogorov's superposition theorem, Linear functional, Lipschitz function",

author = "Aysu Ismayilova and Ismailov, {Vugar E.}",

note = "Publisher Copyright: {\textcopyright} 2024 Elsevier Ltd",

year = "2024",

month = aug,

doi = "10.1016/j.neunet.2024.106333",

language = "English",

volume = "176",

pages = "1--6",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Ltd",

}

TY - JOUR

T1 - On the Kolmogorov neural networks

AU - Ismayilova, Aysu

AU - Ismailov, Vugar E.

PY - 2024/8

Y1 - 2024/8

N2 - In this paper, we show that the Kolmogorov two hidden layer neural network model with a continuous, discontinuous bounded and unbounded activation function in the second hidden layer can precisely represent continuous, discontinuous bounded and all unbounded multivariate functions, respectively.

AB - In this paper, we show that the Kolmogorov two hidden layer neural network model with a continuous, discontinuous bounded and unbounded activation function in the second hidden layer can precisely represent continuous, discontinuous bounded and all unbounded multivariate functions, respectively.

KW - Conjugate operator

KW - Dual space

KW - Indicator function

KW - Kolmogorov's superposition theorem

KW - Linear functional

KW - Lipschitz function

UR - http://www.scopus.com/inward/record.url?scp=85191520922&partnerID=8YFLogxK

U2 - 10.1016/j.neunet.2024.106333

DO - 10.1016/j.neunet.2024.106333

M3 - Article

AN - SCOPUS:85191520922

SN - 0893-6080

VL - 176

SP - 1

EP - 6

JO - Neural Networks

JF - Neural Networks

M1 - 106333

ER -

On the Kolmogorov neural networks

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this