To address the problem that synchronization control is difficult to achieve for neural networks under mismatched initial conditions and heterogeneous distribution of neuronal synaptic weights, a memristor-coupled Hopfield neural network (HNN) model with heterogeneous synaptic weights was constructed in this paper, and synchronous regulation was realized. First, numerical analysis found that the network exhibited multiple dynamic transition modes with the variation of synaptic weights, such as period-doubling bifurcations and boundary crises, indicating that the dynamic behaviors of the neural network could be regulated by tuning synaptic weights. Second, it was found that the energy compensation of the memristor could be dynamically adjusted by the memristor coupling strength, realizing the synchronization behavior of neurons with heterogeneous synaptic weights (heterogeneous neurons for short), thereby achieving information transmission and cooperative processing among heterogeneous neurons. Finally, the synchronization behavior of the coupled network was verified by hardware circuit experiments. This work contributes to deepening the understanding and cognition of the synchronization of coupled heterogeneous neural networks.
ChenY X, YangF F, WangC N. Coherence resonance in a memristive map neuron and adaptive energy regulation[J]. Modern Physics Letters B, 2025, 39(17): 2550008.
[2]
BaoH, HuA H, LiuW B, et al. Hidden bursting firings and bifurcation mechanisms in memristive neuron model with threshold electromagnetic induction[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(2): 502-511.
[3]
LinH R, WangC H, CuiL, et al. Brain-like initial-boosted hyperchaos and application in biomedical image encryption[J]. IEEE Transactions on Industrial Informatics, 2022, 18(12): 8839-8850.
[4]
WuK J, HuangZ X, YanM J. Dynamic behavior of memristor ML neurons and its application in secure communication[J]. The European Physical Journal B, 2024, 97(7): 97.
[5]
MaoY D, DongY J, LuZ Z, et al. Second-order locally active memristor based neuronal circuit[J]. Chaos, Solitons & Fractals, 2025, 195: 116279.
[6]
MouJ, CaoH Z, ZhouN R, et al. An FHN-HR neuron network coupled with a novel locally active memristor and its DSP implementation[J]. IEEE Transactions on Cybernetics, 2024, 54(12): 7333-7342.
[7]
YuY J, BaoH, ShiM, et al. Complex dynamical behaviors of a fractional-order system based on a locally active memristor[J]. Complexity, 2019, 2019: 2051053.
[8]
LaiQ, YangL. Hyperchaos of neuron under local active discrete memristor simulating electromagnetic radiation[J]. Chaos(An Interdisciplinary Journal of Nonlinear Science), 2024, 34(1): 013145.
[9]
BaoH, HuaM J, MaJ, et al. Offset-control plane coexisting behaviors in two-memristor-based Hopfield neural network[J]. IEEE Transactions on Industrial Electronics, 2023, 70(10): 10526-10535.
[10]
ZhuK L, WangY, YangF F. A functional neuron with a linear membrane[J]. The European Physical Journal Special Topics, 2026, 234(28): 8209-8218.
[11]
WangC H, LiangJ H, DengQ L. Dynamics of heterogeneous Hopfield neural network with adaptive activation function based on memristor[J]. Neural Networks, 2024, 178: 106408.
[12]
BaoH, ChenZ G, MaJ, et al. Planar homogeneous coexisting hyperchaos in bi-memristor cyclic Hopfield neural network[J]. IEEE Transactions on Industrial Electronics, 2024, 71(12): 16398-16408.
HuaM J, ZhangY Z, ChenM, et al. Memristive single-neuron model and its memristor-coupled network: homogenously coexisting attractors and parallel-offset synchronization[J]. International Journal of Bifurcation and Chaos, 2022, 32(15): 2250225.
[17]
ZhangY Z, LiuZ, WuH G, et al. Dimensionality reduction analysis for detecting initial effects on synchronization of memristor-coupled system[J]. IEEE Access, 2019, 7: 109689-109698.
[18]
LiK X, BaoB C, MaJ, et al. Synchronization transitions in a discrete memristor-coupled bi-neuron model[J]. Chaos, Solitons & Fractals, 2022, 165: 112861.
[19]
MinF H, ChenC J, BroderickN G R. Coupled homogeneous Hopfield neural networks: simplest model design, synchronization, and multiplierless circuit implementation[J]. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(6): 11632-11639.
[20]
XuY, JiaY, MaJ, et al. Synchronization between neurons coupled by memristor[J]. Chaos, Solitons & Fractals, 2017, 104: 435-442.
[21]
LuJ Q, CaoJ D. Synchronization-based approach for parameters identification in delayed chaotic neural networks[J]. Physica A: Statistical Mechanics and Its Applications, 2007, 382(2): 672-682.
[22]
LinH R, WangC H, HongQ H, et al. A multi-stable memristor and its application in a neural network[J]. IEEE Transactions on Circuits and Systems Ⅱ: Express Briefs, 2020, 67(12): 3472-3476.
ChenC J, BaoH, ZhangY Z, et al. Synchronization and coupling dynamics in memristive homogeneous and heterogeneous Hopfield neural networks[J]. IEEE Transactions on Circuits and Systems I: Regular Papers, 2025, 72(9): 4854-4867.
[25]
WangM J, PengJ W, HeS B, et al. Phase synchronization and dynamic behavior of a novel small heterogeneous coupled network[J]. Fractal and Fractional, 2023, 7(11): 818.