Article
Physics, Multidisciplinary
Sen Fu, Zhengjun Yao, Caixia Qian, Xia Wang
Summary: This paper proposes a star memristive neural network (SMNN) model and analyzes its dynamic characteristics. The results demonstrate that the SMNN can generate complex dynamical behaviors and these behaviors can be changed by adjusting the control parameters and initial values of the memristor. In addition, the theoretical and numerical results are verified by an analog circuit and simulation experiments. Furthermore, a color image encryption scheme based on the SMNN is designed and shows good security performance.
Article
Computer Science, Artificial Intelligence
Qiang Lai, Zhiqiang Wan, Hui Zhang, Guanrong Chen
Summary: This article presents a design of a new Hopfield neural network that can generate multiscroll attractors by utilizing a new memristor as a synapse in the network. The memristor is constructed with hyperbolic tangent functions and its parameters can effectively control the number of double scrolls in an attractor. Numerical analysis reveals amplitude control effects and quantitatively controllable multistability. Furthermore, a novel image encryption scheme based on the proposed memristive neural network is designed and evaluated, demonstrating good encryption performances.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Physics, Multidisciplinary
Zhenhua Hu, Hairong Lin, Chunhua Wang
Summary: This paper presents a network model based on Hopfield neural network and memristor synapse control, which can generate novel grid multi-structure chaotic attractors with simple implementation and complex unit attractor structure. The generation mechanism and dynamical characteristics of the attractors are analyzed, and corresponding analog circuits and image encryption schemes are designed. Experimental results show that the proposed scheme has higher information entropy, key sensitivity, and good application prospect compared to existing schemes.
FRONTIERS IN PHYSICS
(2023)
Article
Computer Science, Hardware & Architecture
Qinghui Hong, Haotian Fu, Yiyang Liu, Jiliang Zhang
Summary: This article proposes an in-memory computing circuit implementation of a complex-valued Hopfield neural network (CHNN) for portrait restoration, which provides high accuracy and efficiency. The circuit utilizes a new memristive array to perform parallel complex-valued multiplication and complex-valued vector-matrix multiplication. The designed CHNN circuit enables large-scale recursive computations. Pspice simulation results demonstrate fast recovery speed, high accuracy, and robustness. The programmability of the memristive array allows different portrait restoration scenarios to be realized.
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
(2023)
Article
Mathematics, Interdisciplinary Applications
Shoukui Ding, Ning Wang, Han Bao, Bei Chen, Huagan Wu, Quan Xu
Summary: This paper proposes a new neural network model based on memristors to simulate the electromagnetic induction effect between neurons. The theoretical analysis and numerical simulations investigate the multistability and various dynamic behaviors of the model, and a simple analog circuit is designed for verification.
CHAOS SOLITONS & FRACTALS
(2023)
Article
Neurosciences
Leila Eftekhari, Mohammad M. Amirian
Summary: This paper presents a method of constructing neural networks using fractional-order memristors, revealing the relationship between network stability and fractional-order value, number of neurons, and network structure through analysis of stability conditions and numerical simulations.
COGNITIVE NEURODYNAMICS
(2023)
Article
Chemistry, Physical
Margarita Mayacela, Leonardo Renteria, Luis Contreras, Santiago Medina
Summary: The memristor, as the fourth fundamental element in electronic circuits, possesses unique memory and resistance properties. While there aren't any electronic solutions based on the memristor, there has been a significant increase in interest for application development. Currently, only numerical Matlab or Spice models and memristor emulators are available for simulating and designing memristor systems.
Article
Engineering, Electrical & Electronic
Jafar Shamsi, Maria Jose Avedillo, Bernabe Linares-Barranco, Teresa Serrano-Gotarredona
Summary: This paper investigates the effect of component mismatches on the performance of differential oscillatory neural networks (DONNs). The results show that mismatches in the components of the differential oscillatory neurons have a greater impact on the performance compared to mismatches in the synaptic circuits. Mismatches in the differential oscillatory neurons result in non-uniformity of the natural frequencies, causing desynchronization and instability.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2023)
Article
Engineering, Mechanical
Mengjiao Wang, Jiwei Peng, Xinan Zhang, Herbert Ho-Ching Iu, Zhijun Li
Summary: In this paper, a novel small heterogeneous coupled network through a memristive synapse is proposed and investigated. The network exhibits multiple stable firing patterns and shows multistability behavior, which has potential applications in brain science and bionics.
NONLINEAR DYNAMICS
(2023)
Article
Mathematics
Qingchao Meng, Huamin Wang
Summary: In this paper, a novel memristor-based non-delay Hopfield neural network with impulsive effects is designed in a quaternion field. Some special inequalities, differential inclusion, Hamilton rules and impulsive system theories are utilized in this manuscript to investigate potential solutions and obtain some sufficient criteria. In addition, through choosing proper mu(t) and impulsive points, the global mu-stability of the solution is discussed and some sufficient criteria are presented by special technologies. Then, from the obtained sufficient criteria of global mu-stability, other stability criteria including exponential stability and power stability can be easily derived. Finally, one numerical example is given to illustrate the feasibility and validity of the derived conclusions.
Article
Mathematics, Applied
Ya Li, Lijun Xie, Ciyan Zheng, Dongsheng Yu, Jason K. Eshraghian
Summary: A novel universal fractional-order mem-elements interface is proposed for constructing three types of fractional-order mem-element emulators, which are validated by PSPICE circuit simulation and printed circuit board hardware experiments. The proposed emulators built based on the universal interface are constructed with a small number of active and passive elements, reducing the cost and promoting the development and application research of fractional-order mem-element emulators for the future.
Article
Engineering, Mechanical
Yue Deng, Shaoyan Li, Peng Zhang, Fang Yuan, Yuxia Li
Summary: This research presents a series of physical memristors with different TiO2 thicknesses, exploring their characteristics and mathematical models in the context of constructing nonlinear and chaotic circuits. A fifth-order memristive circuit is built to reveal the complex coexisting behaviors of multiple kinds of attractors. The numerical simulations are verified through the implementation of a hardware circuit.
NONLINEAR DYNAMICS
(2023)
Article
Engineering, Electrical & Electronic
Hairong Lin, Chunhua Wang, Yichuang Sun, Ting Wang
Summary: This paper presents a novel method for generating n-scroll chaotic attractors. It models a magnetized Hopfield neural network (HNN) with three neurons by introducing an improved multi-piecewise memristor to describe the effect of electromagnetic induction. Theoretical analysis and numerical simulation demonstrate that the memristor-based magnetized HNN can generate multi-scroll chaotic attractors with any number of scrolls, which can be easily adjusted by controlling the memristor parameters. Additionally, complex initial offset boosting behavior is observed in the magnetized HNN. The designed magnetized HNN circuit is capable of generating various typical attractors.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2023)
Article
Engineering, Electrical & Electronic
Ge Shi, Chenyu Wang, Fei Qiao, Rubin Lin, Shien Wu, Mang Shi, Yanwei Sun, Jianqiang Han, Binrui Wang
Summary: A new passive non-ideal floating memristor emulator circuit (MEC) consisting of four transistors, two resistors, and one capacitor is proposed in this paper. The circuit does not require external bias and exhibits Type-II memristive hysteresis loop. Simulation results using the Cadence design environment validate the theoretical study, and practical applications of the MEC in Schmitt trigger circuit and amplitude demodulation circuit are demonstrated.
AEU-INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Junwei Sun, Xiao Xiao, Qinfei Yang, Peng Liu, Yanfeng Wang
Summary: A memristor neural network circuit is designed in this paper to recognize and sequence four characters simultaneously. Through the operation of calculation and iteration submodules, the four-character images distributed by noise can be identified simultaneously. This circuit may provide a reference for the development of new brain-like systems.
AEU-INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATIONS
(2021)
Article
Automation & Control Systems
Qiang Xiao, Zhenkun Huang, Zhigang Zeng
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2019)
Article
Computer Science, Artificial Intelligence
Lihua Shen, Jihong Chen, Zhigang Zeng, Jianzhong Yang, Jian Jin
APPLIED SOFT COMPUTING
(2018)
Article
Computer Science, Hardware & Architecture
Shiping Wen, Shuixin Xiao, Yin Yang, Zheng Yan, Zhigang Zeng, Tingwen Huang
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
(2019)
Article
Computer Science, Artificial Intelligence
Fanghai Zhang, Zhigang Zeng
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2019)
Article
Automation & Control Systems
Shiping Wen, Rui Hu, Yin Yang, Tingwen Huang, Zhigang Zeng, Yong-Duan Song
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2019)
Article
Computer Science, Artificial Intelligence
Yanyi Cao, Yuting Cao, Shiping Wen, Tingwen Huang, Zhigang Zeng
Article
Computer Science, Artificial Intelligence
Yufeng Zhou, Zhigang Zeng
Article
Computer Science, Artificial Intelligence
Minghui Dong, Shiping Wen, Zhigang Zeng, Zheng Yan, Tingwen Huang
Article
Computer Science, Artificial Intelligence
Zhuoling Li, Minghui Dong, Shiping Wen, Xiang Hu, Pan Zhou, Zhigang Zeng
Article
Mathematics, Applied
Sen Zhang, Jiahao Zheng, Xiaoping Wang, Zhigang Zeng
Summary: This study presents a novel non-equilibrium Hindmarsh-Rose neuron model with memristive electromagnetic radiation effect. Through numerical simulations and hardware experiments, it is demonstrated that this model exhibits complex dynamics and high security, making it suitable for real-world applications.
Article
Automation & Control Systems
Leimin Wang, Zhigang Zeng, Ming-Feng Ge
Summary: This paper presents a unified framework for designing sliding-mode control to stabilize delayed memristive neural networks (DMNNs). It is proven that under this framework, the system responses can reach and stay on the designed sliding-mode surface in finite and fixed time. Additionally, the designed sliding-mode control can reject external disturbances effectively.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Mathematics, Interdisciplinary Applications
Sen Zhang, Jiahao Zheng, Xiaoping Wang, Zhigang Zeng
Summary: A novel HR neuron model with memristive electromagnetic induction is proposed in this paper, exhibiting complex dynamics and generating hidden attractors and multistability phenomenon. The detailed investigation includes bifurcation diagrams, Lyapunov exponents, time series, attraction basins, and SE complexity. Circuit simulations and hardware experiments are conducted to demonstrate the theoretical analyses, and a pseudorandom number generator is designed using chaotic sequences from the memristive HR neuron model.
CHAOS SOLITONS & FRACTALS
(2021)
Article
Computer Science, Artificial Intelligence
Depeng Li, Tianqi Wang, Junwei Chen, Kenji Kawaguchi, Cheng Lian, Zhigang Zeng
Summary: This paper investigates a novel paradigm called multi-view class incremental learning (MVCIL), which addresses the challenges of catastrophic forgetting and interference in multi-view learning. The paper proposes a randomization-based representation learning technique and selective weight consolidation to tackle these challenges. Extensive experiments validate the effectiveness of the approach.
INFORMATION FUSION
(2024)
Article
Automation & Control Systems
Shiping Wen, Huaqiang Wei, Yin Yang, Zhenyuan Guo, Zhigang Zeng, Tingwen Huang, Yiran Chen
Summary: This paper presents a complete solution for the hardware design of a memristor-based MLSTM network, utilizing parameter sharing mechanism and efficient implementation of memristor crossbars to reduce hardware design scale. Experimental results validate the effectiveness of the system.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Automation & Control Systems
Junwei Sun, Gaoyong Han, Zhigang Zeng, Yanfeng Wang
IEEE TRANSACTIONS ON CYBERNETICS
(2020)
Article
Physics, Multidisciplinary
Tinggui Chen, Baizhan Xia, Dejie Yu, Chuanxing Bi
Summary: This study proposes a gradient phononic crystal structure for enhanced acoustic sensing. By breaking the symmetry of the PC structure, topologically protected edge states are introduced, resulting in topological acoustic rainbow trapping. The robustness and enhancement properties are verified numerically and experimentally.