Coupling Heterogeneous Neural Networks With Memristors

This paper proposes a novel approach for cascading Hopfield and Hindmarsh-Rose neural networks using memristive synapses. The model integrates two distinct neural networks, each consisting of two identical neurons. First, we design a memristor and analyze its memristive characteristics. We then deve...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Zhang, Rongli Jiang, Yike Ma, Xiangkai Pu, Zhongyi Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10918951/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850275804886335488
author Li Zhang
Rongli Jiang
Yike Ma
Xiangkai Pu
Zhongyi Li
author_facet Li Zhang
Rongli Jiang
Yike Ma
Xiangkai Pu
Zhongyi Li
author_sort Li Zhang
collection DOAJ
description This paper proposes a novel approach for cascading Hopfield and Hindmarsh-Rose neural networks using memristive synapses. The model integrates two distinct neural networks, each consisting of two identical neurons. First, we design a memristor and analyze its memristive characteristics. We then develop the Hopfield and Hindmarsh-Rose networks with dual neurons, utilizing memristors to couple these sub-networks, forming a new four-neuron neural network. The equilibrium points and system stability are thoroughly analyzed. The dynamic behavior of the network is examined through bifurcation diagrams, two-parameter bifurcation plots, Lyapunov exponents, and phase diagrams, revealing phenomena such as chaos, periodicity, period-doubling bifurcations, and alternating-period chaos. To validate the numerical simulations, we implement the phase diagram on an STM32 hardware platform. Finally, we propose a DNA-based image encryption algorithm leveraging chaotic sequences generated by the network. The performance analysis of encrypted images demonstrates that the algorithm offers strong robustness during transmission and effective resistance against attacks, ensuring privacy and security.
format Article
id doaj-art-bb617067fa1a490a93c2975d65a52c92
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-bb617067fa1a490a93c2975d65a52c922025-08-20T01:50:33ZengIEEEIEEE Access2169-35362025-01-0113538355384810.1109/ACCESS.2025.354997810918951Coupling Heterogeneous Neural Networks With MemristorsLi Zhang0https://orcid.org/0000-0003-1367-4031Rongli Jiang1https://orcid.org/0009-0002-4622-263XYike Ma2Xiangkai Pu3Zhongyi Li4School of Integrated Circuits, Anhui University, Hefei, ChinaSchool of Integrated Circuits, Anhui University, Hefei, ChinaSchool of Integrated Circuits, Anhui University, Hefei, ChinaChina National Building Material (CNBM) Environmental Protection Research Institute (Jiangsu) Company Ltd., Yancheng, ChinaSchool of Integrated Circuits, Anhui University, Hefei, ChinaThis paper proposes a novel approach for cascading Hopfield and Hindmarsh-Rose neural networks using memristive synapses. The model integrates two distinct neural networks, each consisting of two identical neurons. First, we design a memristor and analyze its memristive characteristics. We then develop the Hopfield and Hindmarsh-Rose networks with dual neurons, utilizing memristors to couple these sub-networks, forming a new four-neuron neural network. The equilibrium points and system stability are thoroughly analyzed. The dynamic behavior of the network is examined through bifurcation diagrams, two-parameter bifurcation plots, Lyapunov exponents, and phase diagrams, revealing phenomena such as chaos, periodicity, period-doubling bifurcations, and alternating-period chaos. To validate the numerical simulations, we implement the phase diagram on an STM32 hardware platform. Finally, we propose a DNA-based image encryption algorithm leveraging chaotic sequences generated by the network. The performance analysis of encrypted images demonstrates that the algorithm offers strong robustness during transmission and effective resistance against attacks, ensuring privacy and security.https://ieeexplore.ieee.org/document/10918951/Hopfield neural networkmemristorHindmarsh-Rose neural networkhardware implementationimage encryption
spellingShingle Li Zhang
Rongli Jiang
Yike Ma
Xiangkai Pu
Zhongyi Li
Coupling Heterogeneous Neural Networks With Memristors
IEEE Access
Hopfield neural network
memristor
Hindmarsh-Rose neural network
hardware implementation
image encryption
title Coupling Heterogeneous Neural Networks With Memristors
title_full Coupling Heterogeneous Neural Networks With Memristors
title_fullStr Coupling Heterogeneous Neural Networks With Memristors
title_full_unstemmed Coupling Heterogeneous Neural Networks With Memristors
title_short Coupling Heterogeneous Neural Networks With Memristors
title_sort coupling heterogeneous neural networks with memristors
topic Hopfield neural network
memristor
Hindmarsh-Rose neural network
hardware implementation
image encryption
url https://ieeexplore.ieee.org/document/10918951/
work_keys_str_mv AT lizhang couplingheterogeneousneuralnetworkswithmemristors
AT ronglijiang couplingheterogeneousneuralnetworkswithmemristors
AT yikema couplingheterogeneousneuralnetworkswithmemristors
AT xiangkaipu couplingheterogeneousneuralnetworkswithmemristors
AT zhongyili couplingheterogeneousneuralnetworkswithmemristors