Numerical Solution of Fractional Hopfield Neural Networks Using Reproducing Kernel Hilbert Space Method

Yassamine Chellouf; Banan Maayah; Omar Abu Arqub; Shaher Mohammad Momani

Numerical Solution of Fractional Hopfield Neural Networks Using Reproducing Kernel Hilbert Space Method

Yassamine Chellouf
, Banan Maayah
, Omar Abu Arqub
, Shaher Mohammad Momani

Université AbdelHafid Boussouf - Mila
University of Jordan
Al-Balqa Applied University

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

Abstract

Artificial neural networks (ANN) consist of a group of the virtual neurons that are designed by computerized programs which use a variety of mathematical fractional equations. In this paper, we introduce the Reproducing Kernel Hilbert Space (RKHS) method for solving some certain fractional differential systems in the artificial neural networks field, which is the Hopfield network, using the conformable derivative.

Original language	English
Pages (from-to)	460-472
Number of pages	13
Journal	Nonlinear Dynamics and Systems Theory
Volume	24
Issue number	5
State	Published - 2024
Externally published	Yes

Keywords

Reproducing Kernel Hilbert Space Method (RKHSM)
artificial neural networks
chaotic attractors
differential systems
fractional derivative

Cite this

@article{f5f8ef78e4d44706a0fa07f7d153cbfa,

title = "Numerical Solution of Fractional Hopfield Neural Networks Using Reproducing Kernel Hilbert Space Method",

abstract = "Artificial neural networks (ANN) consist of a group of the virtual neurons that are designed by computerized programs which use a variety of mathematical fractional equations. In this paper, we introduce the Reproducing Kernel Hilbert Space (RKHS) method for solving some certain fractional differential systems in the artificial neural networks field, which is the Hopfield network, using the conformable derivative.",

keywords = "Reproducing Kernel Hilbert Space Method (RKHSM), artificial neural networks, chaotic attractors, differential systems, fractional derivative",

author = "Yassamine Chellouf and Banan Maayah and Arqub, \{Omar Abu\} and Momani, \{Shaher Mohammad\}",

note = "Publisher Copyright: {\textcopyright} 2024 InforMath Publishing Group.",

year = "2024",

language = "English",

volume = "24",

pages = "460--472",

journal = "Nonlinear Dynamics and Systems Theory",

issn = "1562-8353",

publisher = "InforMath Publishing Group",

number = "5",

}

TY - JOUR

T1 - Numerical Solution of Fractional Hopfield Neural Networks Using Reproducing Kernel Hilbert Space Method

AU - Chellouf, Yassamine

AU - Maayah, Banan

AU - Arqub, Omar Abu

AU - Momani, Shaher Mohammad

PY - 2024

Y1 - 2024

N2 - Artificial neural networks (ANN) consist of a group of the virtual neurons that are designed by computerized programs which use a variety of mathematical fractional equations. In this paper, we introduce the Reproducing Kernel Hilbert Space (RKHS) method for solving some certain fractional differential systems in the artificial neural networks field, which is the Hopfield network, using the conformable derivative.

AB - Artificial neural networks (ANN) consist of a group of the virtual neurons that are designed by computerized programs which use a variety of mathematical fractional equations. In this paper, we introduce the Reproducing Kernel Hilbert Space (RKHS) method for solving some certain fractional differential systems in the artificial neural networks field, which is the Hopfield network, using the conformable derivative.

KW - Reproducing Kernel Hilbert Space Method (RKHSM)

KW - artificial neural networks

KW - chaotic attractors

KW - differential systems

KW - fractional derivative

UR - https://www.scopus.com/pages/publications/85214379475

M3 - Article

AN - SCOPUS:85214379475

SN - 1562-8353

VL - 24

SP - 460

EP - 472

JO - Nonlinear Dynamics and Systems Theory

JF - Nonlinear Dynamics and Systems Theory

IS - 5

ER -

Numerical Solution of Fractional Hopfield Neural Networks Using Reproducing Kernel Hilbert Space Method

Abstract

Keywords

Other files and links

Fingerprint

Cite this