检索结果-内蒙古大学图书馆

MA-MNN: Multi-flow attentive memristive neural network for multi-task image restoration

Signal Processing: Image Communication 2025年 138卷

作者： He, Peng Zhang, Lin Yang, Yu Zhou, Yue Duan, Shukai Hu, Xiaofang College of Artificial Intelligence Southwest University Chongqing400715 China Brain-inspired Computing & Intelligent Control of Chongqing Key Lab Chongqing400715 China Ministry of Education China

Images taken in rainy, hazy, and low-light environments severely hinder the performance of outdoor computer vision systems. Most data-driven image restoration methods are task-specific and computationally intensive, whereas the capture and processing of degraded images occur largely in end-side devices with limited computing resources. Motivated by addressing the above issues, a novel software and hardware co-designed image restoration method named multi-flow attentive memristive neural network (MA-MNN) is proposed in this paper, which combines a deep learning algorithm and the nanoscale device memristor. The multi-level complementary spatial contextual information is exploited by the multi-flow aggregation block. The dense connection design is adopted to provide smooth transportation across units and alleviate the vanishing-gradient. The supervised calibration block is designed to facilitate achieving the dual-attention mechanism that helps the model identify and re-calibrate the transformed features. Besides, a hardware implementation scheme based on memristors is designed to provide low energy consumption solutions for embedded applications. Extensive experiments in image deraining, image dehazing and low-light image enhancement have shown that the proposed method is highly competitive with over 20 state-of-the-art methods. © 2025 Elsevier B.V.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Physical mechanisms and integration design of memristors

引用

Materials Today Nano 2025年 30卷

作者： Wang, Mengna Wang, Kun Sun, Bai Zhou, Guangdong Cao, Zelin Gao, Kaikai Ren, Fenggang Chen, Xiaoliang Li, Xiangming Shao, Jinyou Frontier Institute of Science and Technology and Interdisciplinary Research Center of Frontier Science and Technology Xi'an Jiaotong University Shaanxi Xi'an710049 China Micro-and Nano-technology Research Center State Key Laboratory for Manufacturing Systems Engineering Xi'an Jiaotong University Shaanxi Xi'an710049 China College of Artificial Intelligence Brain-inspired Computing & Intelligent Control of Chongqing Key Lab Southwest University Chongqing400715 China National Local Joint Engineering Research Center for Precision Surgery & Regenerative Medicine The First Affiliated Hospital of Xi'an Jiaotong University Shaanxi Xi'an710049 China

Memristors with threshold transition behavior and rich dynamics are ideal candidates for simulating biological pulse neurons and constructing efficient neuromorphic systems. Based on changes in material structure, charge distribution, molecular polarization and other physical states, new integrated memory-computing devices have been constructed and applied to the sensor-memory-computing integrated systems. In this review, we first discuss the classification of memristive materials from the perspective of device structure design and focus on introducing the working mechanisms of valence variation, polarization, and carrier transfer covered internally. Further, the latest progress of memristors with multi-physical mechanisms is comprehensively summarized, including the formation/fracture of conductive filaments, carrier capture/release, polarization/depolarization. In particular, it is discussed in detail the principles and applications of memristors with different working mechanisms for constructing neuromorphic systems. Finally, the potential challenges and opportunities that may exist in the development of memristors in the coming years are discussed in depth. © 2025 Elsevier Ltd

关键词： Molecular structure

来源：评论

学校读者我要写书评

暂无评论

A spintronic memristive circuit on the optimized RBF-MLP neural network

引用

Chinese Physics B 2022年第11期31卷 272-283页

作者： Yuan Ge Jie Li Wenwu Jiang Lidan Wang Shukai Duan School of Artificial Intelligence Southwest UniversityChongqing 400715China Chongqing Brain Science Collaborative Innovation Center Chongqing 400715China Brain-inspired Computing and Intelligent Control of Chongqing Key Laboratory Chongqing 400715China National&Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing 400715China

A radial basis function network(RBF)has excellent generalization ability and approximation accuracy when its parameters are set ***,when relying only on traditional methods,it is difficult to obtain optimal network parameters and construct a stable model as *** view of this,a novel radial basis neural network(RBF-MLP)is proposed in this *** connecting two networks to work cooperatively,the RBF’s parameters can be adjusted adaptively by the structure of the multi-layer perceptron(MLP)to realize the effect of the backpropagation updating ***,a genetic algorithm is used to optimize the network’s hidden layer to confirm the optimal neurons(basis function)number *** addition,a memristive circuit model is proposed to realize the neural network’s operation based on the characteristics of spin *** is verified that the network can adaptively construct a network model with outstanding robustness and can stably achieve 98.33%accuracy in the processing of the Modified National Institute of Standards and Technology(MNIST)dataset classification *** experimental results show that the method has considerable application value.

关键词： radial basis function network(RBF) genetic algorithm spintronic memristor memristive circuit

来源：评论

学校读者我要写书评

暂无评论

Memristor-based multi-synaptic spiking neuron circuit for spiking neural network

引用

Chinese Physics B 2022年第4期31卷 225-233页

作者： Wenwu Jiang Jie Li Hongbo Liu Xicong Qian Yuan Ge Lidan Wang Shukai Duan College of Artificial Intelligence Southwest UniversityChongqing 400715China National&Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing 400715China Brain-inspired Computing and Intelligent Control of Chongqing Key Laboratory Chongqing 400715China Chongqing Brain Science Collaborative Innovation Center Chongqing 400715China

Spiking neural networks(SNNs) are widely used in many fields because they work closer to biological ***,due to its computational complexity,many SNNs implementations are limited to computer ***,this paper proposes a multi-synaptic circuit(MSC) based on memristor,which realizes the multi-synapse connection between neurons and the multi-delay transmission of pulse *** synapse circuit participates in the calculation of the network while transmitting the pulse signal,and completes the complex calculations on the software with ***,a new spiking neuron circuit based on the leaky integrate-and-fire(LIF) model is designed in this *** amplitude and width of the pulse emitted by the spiking neuron circuit can be adjusted as *** combination of spiking neuron circuit and MSC forms the multi-synaptic spiking neuron(MSSN).The MSSN was simulated in PSPICE and the expected result was obtained,which verified the feasibility of the ***,a small SNN was designed based on the mathematical model of *** the SNN is trained and optimized,it obtains a good accuracy in the classification of the IRIS-dataset,which verifies the practicability of the design in the network.

关键词： memristor multi-synaptic circuit spiking neuron spiking neural network(SNN)

来源：评论

学校读者我要写书评

暂无评论

Exploring reservoir computing:Implementation via double stochastic nanowire networks

引用

Chinese Physics B 2024年第3期33卷 572-582页

作者：唐健峰夏磊李广隶付军段书凯王丽丹 College of Artificial Intelligence Southwest UniversityChongqing 400715China Brain-inspired Computing & Intelligent Control of Chongqing Key Laboratory Chongqing 400715China National & Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing 400715China Chongqing Brain Science Collaborative Innovation Center Chongqing 400715China Key Laboratory of Luminescence Analysis and Molecular Sensing Ministry of EducationSouthwest UniversityChongqing 400715China State Key Laboratory of Intelligent Vehicle Safety Technology Chongqing 400715China

Neuromorphic computing,inspired by the human brain,uses memristor devices for complex *** studies show that self-organizing random nanowires can implement neuromorphic information processing,enabling data *** paper presents a model based on these nanowire networks,with an improved conductance variation *** suggest using these networks for temporal information processing via a reservoir computing scheme and propose an efficient data encoding method using voltage *** nanowire network layer generates dynamic behaviors for pulse voltages,allowing time series prediction *** experiment uses a double stochastic nanowire network architecture for processing multiple input signals,outperforming traditional reservoir computing in terms of fewer nodes,enriched dynamics and improved prediction *** results confirm the high accuracy of this architecture on multiple real-time series datasets,making neuromorphic nanowire networks promising for physical implementation of reservoir computing.

关键词： double-layer stochastic(DS)nanowire network architecture neuromorphic computation nanowire network reservoir computing time series prediction

来源：评论

学校读者我要写书评

暂无评论

Memristor-based hyper-chaotic circuit for image encryption

引用

Chinese Physics B 2020年第11期29卷 259-270页

作者： Jiao-Jiao Chen Deng-Wei Yan Shu-Kai Duan Li-Dan Wang College of Electronic and Information Engineering Southwest UniversityChongqing 400715China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Southwest UniversityChongqing 400715China Intelligent Transmission and Control Technology Joint Engineering Laboratory Chongqing 400715China Brain-inspired Computing and Intelligent Control Chongqing Key Laboratory Chongqing 400715China Chongqing Collaborative Innovation Center for Brain Science Chongqing 400715China School of Artificial Intelligence Southwest UniversityChongqing 400715China

The memristor is a kind of non-linear element with memory function,which can be applied to chaotic systems to increase signal randomness and *** this paper,a new four-dimensional hyper-chaotic system is designed based on a flux controlled memristor model,which can generate complex chaotic *** basic dynamic theory analysis and numerical simulations of the system,such as the stability of equilibrium points,the Lyapunov exponents and dimension,Poincare maps,the power spectrum,and the waveform graph prove that it has rich dynamic ***,the circuit implementation of this system is *** consistency of simulation program with integrated circuit emphasis(SPICE)simulation and numerical analysis proves the ability to generate ***,a new image encryption scheme is designed by using the memristor-based hyper-chaotic system proposed in this *** scheme involves a total of two *** using different security analysis factors,the proposed algorithm is compared with other image encryption schemes,including correlation analysis,information entropy,*** results show that the proposed image encryption scheme has a large key space and presents a better encryption effect.

关键词： memristor SPICE simulation hyper-chaotic system image encryption

来源：评论

学校读者我要写书评

暂无评论

Recovery of Distributed Dynamic Bandwidth Graph Signal 23

Recovery of Distributed Dynamic Bandwidth Graph Signal

引用

7th International Conference on Digital Signal Processing, ICDSP 2023

作者： Liu, Zhao Chen, Feng College of Artificial Intelligence Southwest University China College of Artificial Intelligence Brain Inspired Computing and Intelligent Control Key Laboratory Southwest University Chongqing Collaborative Innovation Center for Brain Science China

ISBN: (纸本)9781450398626

The recovery of signal samples from available noisy samples is a fundamental problem in signal processing. This process is known as graph signal recovery. In this paper, a distributed dynamic bandwidth graph signal recovery method is proposed. We consider the case where the bandwidth of the graph signal is unknown, i.e., the frequency domain signal is time-varying. In other words, the frequency domain signal is sparse, and the sparsity is variable at different times. The convex sparsity regularization term is used to promote the sparsity of the signal, and the time-varying bandwidth graph signal can be tracked and recovered. The performance of the proposed algorithm in the mean is theoretically analyzed. Meanwhile, numerical results show the effectiveness of the proposed algorithms and validate the theoretical results. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Secure Distributed Unscented Kalman Filter Against Cyber Attacks: DUKF with cluster-based attack detection strategy 23

Secure Distributed Unscented Kalman Filter Against Cyber Att...

引用

7th International Conference on Digital Signal Processing, ICDSP 2023

作者： Zhao, Hongyu Chen, Feng Ye, Ming College of Artificial Intelligence Southwest University Chongqing China College of Artificial Intelligence Brain-Inspired Computing and Intelligent Control Key Laboratory Southwest University Chongqing Collaborative Innovation Center for Brain Science Chongqing China

ISBN: (纸本)9781450398626

During the past decades, distributed unscented Kalman filter (DUKF) has developed rapidly in the field of position tracking in sensor networks. In this paper, we propose a DUKF with cluster-based attack detection strategy algorithm for state estimation under malicious network attacks. The application of the attack detection algorithm with two layers of cycling mechanism to the state estimation attack detection guarantees the security and reliability of the converged data. A good estimation of the situation in which the information of the secure node is unknown is achieved by measuring 4 steps: update, cluster-based attraction detection, information fusion and prediction. Moreover, the simulation results show that the method is robust to random attacks, FDI attacks, reverse attacks and delayed attacks. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

MC-CapsNet : Low-level Pooling and High-level Fusion of Multi-columns Capsule Network

MC-CapsNet : Low-level Pooling and High-level Fusion of Mult...

引用

2021 International Conference on Neuromorphic computing, ICNC 2021

作者： Li, Ke Duan, Shukai Wang, Lidan Wang, Yining Wang, Shu College of Artificial Intelligence Southwest University Brain-inspired Computing and Intelligent Control of Chongqing Key Lab National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing Brain Science Collaborative Innovation Center Chongqing China College of Electronic and Information Engineering Southwest University Chongqing China

ISBN: (纸本)9781665412872

Capsule network is a new type of neural network structure. The biggest feature of capsule network is 'vector in vector out', which replaces the previous 'scalar in scalar out'. The pristine capsule network completely discards the pooling layers and uses a convolutional kernel size of 9 × 9 to increase the perceptual field However, since the original capsule network has only two feature extraction layers, it cannot extract high level abstract features of objects, which are very important for image classification. Moreover, the original capsule network completely discards the use of pooling layers. Based on the above problems, we propose a multi-column capsule network (MC-CapsNet) with low-level pooling and high-level fusion. Unlike the traditional capsule network, MC-CapsNet has the following features: (a)MC-CapsNet consists of two columns of capsule network: the primary column of capsule network extracts high-level impalpable features;the other column of capsule network extracts subordinate shallow features (b)Pooling operation is added to the initial two convolutional layers of the two columns of capsule network (c)Using the high-level theoretical features extracted from the first capsule network to fuse features with the low-level surface layers extracted from the second capsule network to achieve feature complementarily (d)We add the elements of the digital capsule layers in the two-column capsule network to increase the probability of object features being detected by the capsule. The experimental results show that the classification accuracy of MC-CapsNet reaches 87.96% and 94.42% on the CIFAR10 and FashionMNIST datasets. © 2021 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Synergistic enhancement of memristive behavior and self-rectifying effect in MnO2 based memristor by ions doping method

引用

Applied Materials Today 2025年 44卷

作者： Yang, Bo Cao, Zelin Sun, Bai Gao, Kaikai Wang, Mengna Zhou, Guangdong Lv, Jian Luo, Sihai Chen, Xiaoliang Li, Xiangming Shao, Jinyou Frontier Institute of Science and Technology and Interdisciplinary Research Center of Frontier Science and Technology Xi'an Jiaotong University Shaanxi Xi'an710049 China Micro-and Nano-technology Research Center State Key Laboratory for Manufacturing Systems Engineering Xi'an Jiaotong University Shaanxi Xi'an710049 China College of Artificial Intelligence Brain-inspired Computing & Intelligent Control of Chongqing Key Lab Southwest University Chongqing400715 China

As one of the most promising candidates to replace the traditional von Neumann architecture, memristor shows considerable potential in neuromorphic computing, neural networks, brain-like chips, artificial intelligence, and information storage. However, its performance in terms of ultra-high stability, scalability, and extended switching windows has yet to be broken through, limiting its practical applications. In this work, it is investigated in detail the effect of Cu2+/Zn2+ ions doping on the memristive performance in the Ag/δ-MnO2/Ti devices with three different doping concentrations. We found that the optimal doping concentration can significantly improve the stability and resistance switching ratio of the device. Through first principles analysis, it is further confirmed that the main mechanism for the improvement in device switching ratio is the reduction of MnO bandgap caused by Cu2+/Zn2+ ions doping. Finally, we proposed that the formation of CuO/ZnO buffer layer through the interaction between Cu2+/Zn2+ ions and O2- ions is the key factor leading to the transition of threshold voltage from self-rectification to memristive behavior. Therefore, this work provides an in-deep understanding of the theory of metal ions doping in memristive device, which adds a new strategy to improve the memristive performance of the device in neuromorphic applications. © 2025 Elsevier Ltd

关键词： Electric rectifiers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：