JZUS - Journal of Zhejiang University SCIENCE

Journal of Zhejiang University SCIENCE A

Accepted manuscript available online (unedited version)

A heterogeneous cyclic Hopfield neural network without self-connections

Author(s): Yunzhen ZHANG¹, Chunlong ZHOU^1, ², Han BAO², Guangzhe ZHAO¹, Bocheng BAO²
Affiliation(s): ¹School of Information Engineering, Xuchang University, Xuchang 461000, China ²Wang Zheng School of Microelectronics, Changzhou University, Changzhou 213159, China
Corresponding email(s): Han BAO, hanbao@cczu.edu.cn
Key Words: Activation function; Analog circuit; Chaos; Cyclic Hopfield neural network; Multi-scroll chaotic attractor

Share this article to： More <<< Previous Paper \|Next Paper >>>

Yunzhen ZHANG¹, Chunlong ZHOU^1,², Han BAO², Guangzhe ZHAO¹, Bocheng BAO². A heterogeneous cyclic Hopfield neural network without self-connections[J]. Journal of Zhejiang University Science A,in press.Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/jzus.A2500350

@article{title="A heterogeneous cyclic Hopfield neural network without self-connections",
author="Yunzhen ZHANG¹, Chunlong ZHOU^1,², Han BAO², Guangzhe ZHAO¹, Bocheng BAO²",
journal="Journal of Zhejiang University Science A",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/jzus.A2500350"
}

%0 Journal Article
%T A heterogeneous cyclic Hopfield neural network without self-connections
%A Yunzhen ZHANG¹
%A Chunlong ZHOU^1
%A²
%A Han BAO²
%A Guangzhe ZHAO¹
%A Bocheng BAO²
%J Journal of Zhejiang University SCIENCE A
%P
%@ 1673-565X
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/jzus.A2500350"

TY - JOUR
T1 - A heterogeneous cyclic Hopfield neural network without self-connections
A1 - Yunzhen ZHANG¹
A1 - Chunlong ZHOU^{1
A1 -}²
A1 - Han BAO²
A1 - Guangzhe ZHAO¹
A1 - Bocheng BAO²
J0 - Journal of Zhejiang University Science A
SP -
EP -
%@ 1673-565X
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/jzus.A2500350"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: We propose a three-neuron heterogeneous cyclic Hopfield neural network (het-CHNN) utilizing three different activation functions: the hyperbolic tangent, sine, and cosine functions. The network's globally uniformly ultimately boundedness is proved theoretically, and its chaotic dynamics are explored through numerical simulations and analog experiments. The numerical results demonstrate that the het-CHNN displays chaotic dynamics and multi-scroll chaotic attractors. Subsequently, the het-CHNN is implemented in an analog circuit and hardware experiments are performed to verify the previous numerical results. Notably, the het-CHNN successfully resolves the issue of the absence of chaos in a three-neuron CHNN, and currently appears to be the simplest three-neuron HNN that can generate chaos.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference