期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到185,397篇文章
< 1 2 … 250 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Two-terminal ferroelectric memristors:material innovation,mechanistic breakthroughs,new opportunities for intelligent computing 认领 引用
1
作者 Jiaming Zhang Chaocheng Sun +4 位作者 Yan Jing Yifei Pei Jianbin Xu Xiaobing Yan Jianhui Zhao 《Science Bulletin》 SCIE EI CAS CSCD 2026年第13期3424-3452,共29页
The accelerating demand for intelligent and energy-efficient computing is driving the search for alternatives to the traditional von Neumann architecture,which is increasingly constrained by the physical separation of... The accelerating demand for intelligent and energy-efficient computing is driving the search for alternatives to the traditional von Neumann architecture,which is increasingly constrained by the physical separation of memory and processing units.Among emerging solutions,ferroelectric memristors have attracted considerable attention owing to their continuously tunable non-volatile data storage enabled by polarization-strength modulation and their electrically adjustable resistance governed by ferroelectric polarization switching.Furthermore,the long-term polarization retention of ferroelectric materials,the high endurance of the devices,and the hysteretic,accumulative,and plastic nature of polarization switching make them ideal candidates for implementing memory and neuromorphic computing paradigms.This review examines the latest advances in ferroelectric memristor research,including device physics,material systems,and ferroelectric modulation.We also highlight the neuromorphic applications of such devices in synaptic simulation and multimodal integrated perception,as well as their implementation in large-scale integrated arrays.The outlook discusses potential future directions of ferroelectric memristors for the development of high-performance and low-power intelligent systems from the perspectives of materials,devices,algorithms,and architectures.This work contributes to advancing the understanding of cutting-edge developments in ferroelectric memristors and provides a theoretical foundation and innovative insights for breakthroughs in next-generation low-power intelligent computing architectures. 展开更多
关键词 Ferroelectric memristors Ferroelectric materials Ferroelectric polarization Neuromorphic applications Intelligent computing
暂未订购 下载PDF
Data-driven computing ligament loading mechanisms:integration of the computational ligament mechanics models with deep learning 认领 引用
2
作者 Datao Xu Huiyu Zhou +7 位作者 Yi Yuan Zanni Zhang Tianle Jie Zhifeng Zhou Zixiang Gao Liangliang Xiang Meizi Wang Yaodong Gu 《Acta Mechanica Sinica》 SCIE EI CAS CSCD 2026年第5期628-672,共45页
Ankle injuries account for more than 25%of sports-related injuries.However,there is a lack of computational mechanics modeling and assessment tools for the ligament loading mechanism(LLM)caused by ankle injury.This st... Ankle injuries account for more than 25%of sports-related injuries.However,there is a lack of computational mechanics modeling and assessment tools for the ligament loading mechanism(LLM)caused by ankle injury.This study combines medical imaging data to construct the subject-specific ankle musculoskeletal model,which considers the subject's individualized characteristics and ligamentous attributes.Furthermore,we developed the structural constitutive model to restore the nonlinear short-term viscoelastic properties of the ligament-dense connective tissue,which can more realistically revert the LLM and reveal the mechanical properties of ankle injury.Based on the computational ligament mechanics(CLM)model,we developed a deep learning-based prediction model to predict LLM by CLM data-driven modeling.The modeling simulation results are highly consistent with the calculation results from the dual fluoroscopic imaging system,which demonstrated that the CLM model has high accuracy.The data-driven modeling performs exceptionally well in predicting ligament loading forces.The findings indicate that the constructed CLM data-driven model has the potential to enhance the accuracy and safety of ankle rehabilitation robots,while also providing personalized,dynamically adjusted rehabilitation training programs.The proposed comprehensive solutions would bring benefits to more patients with sports injuries and the general rehabilitation population,and promote the development and advancement of the research field of CLM and biomechanical variable prediction. 展开更多
关键词 Computational ligament mechanics Subject-specific musculoskeletal model Structural constitutive model Ankle ligament injury mechanisms Biomechanical variable prediction
暂未订购 下载PDF
Mechanical Properties Analysis of Flexible Memristors for Neuromorphic Computing 认领 引用 被引量：3
3
作者 Zhenqian Zhu Jiheng Shui +1 位作者 Tianyu Wang Jialin Meng 《Nano-Micro Letters》 SCIE EI CAS CSCD 2026年第1期53-79,共27页
The advancement of flexible memristors has significantly promoted the development of wearable electronic for emerging neuromorphic computing applications.Inspired by in-memory computing architecture of human brain,fle... The advancement of flexible memristors has significantly promoted the development of wearable electronic for emerging neuromorphic computing applications.Inspired by in-memory computing architecture of human brain,flexible memristors exhibit great application potential in emulating artificial synapses for highefficiency and low power consumption neuromorphic computing.This paper provides comprehensive overview of flexible memristors from perspectives of development history,material system,device structure,mechanical deformation method,device performance analysis,stress simulation during deformation,and neuromorphic computing applications.The recent advances in flexible electronics are summarized,including single device,device array and integration.The challenges and future perspectives of flexible memristor for neuromorphic computing are discussed deeply,paving the way for constructing wearable smart electronics and applications in large-scale neuromorphic computing and high-order intelligent robotics. 展开更多
关键词 Flexible memristor Neuromorphic computing Mechanical property Wearable electronics
暂未订购 下载PDF
Self-Rectifying Memristors for Beyond-CMOS Computing:Mechanisms,Materials,and Integration Prospects 认领 引用
4
作者 Guobin Zhang Xuemeng Fan +8 位作者 Zijian Wang Pengtao Li Zhejia Zhang Bin Yu Dawei Gao Desmond Loke Shuai Zhong Qing Wan Yishu Zhang 《Nano-Micro Letters》 SCIE EI CAS CSCD 2026年第6期293-335,共43页
The deceleration of Moore's law and the energy–latency drawbacks of the von Neumann bottleneck have heightened the pursuit for beyond-CMOS designs that integrate memory and compute.Self-rectifying memristors(SRMs... The deceleration of Moore's law and the energy–latency drawbacks of the von Neumann bottleneck have heightened the pursuit for beyond-CMOS designs that integrate memory and compute.Self-rectifying memristors(SRMs)have emerged as promising building blocks for high-performance,low-power systems by combining resistive switching with intrinsic diode-like behavior.Their unidirectional conduction inhibits sneak-path currents in crossbar arrays devoid of external selectors,while nonlinear I–V characteristics,adjustable conductance states,low operating voltages,and rapid switching facilitate efficient vector–matrix operations,neuromorphic plasticity,and hardware security primitives.This review synthesizes the working mechanisms of SRMs,surveys material,and structural strategies and compares device metrics relevant to array-scale deployment(rectification ratio,nonlinearity,endurance,retention,variability,and operating voltage).We assess SRM-enabled in-memory computing and neuromorphic applications,as well as security functions such as physical unclonable functions and reconfigurable cryptographic primitives.Integration pathways toward CMOS compatibility are analyzed,including back-end-of-line thermal budgets,uniformity,write disturb mitigation,and reliability.Finally,we outline key challenges and opportunities:materials/architecture co-design,precision analog training,stochasticity control/exploitation,3D stacking,and standardized benchmarking that can accelerate large-scale SRM adoption.Through the use of specialized materials and structural optimization,SRMs are set to provide selector-free,densely integrated,and energy-efficient hardware for future information processing. 展开更多
关键词 Self-rectifying memristor Beyond-CMOS CMOS compatibility In-memory computing Neuromorphic computing
暂未订购 下载PDF
GCN and DRL based on dependent task offloading mechanism in edge computing 认领 引用
5
作者 Ruiqi Tong Shaoyong Guo +2 位作者 Xuesong Qiu Feng Qi Dongxiao Yu 《Digital Communications and Networks》 SCIE EI CSCD 2026年第3期397-404,共8页
Task offloading is critical for optimizing resource allocation in edge computing systems.In practical scenarios,user applications often comprise multiple interdependent tasks,where both task dependencies and paralleli... Task offloading is critical for optimizing resource allocation in edge computing systems.In practical scenarios,user applications often comprise multiple interdependent tasks,where both task dependencies and parallelism strongly affect offloading decisions.This paper presents a novel dependent task offloading framework for multiedge server environments.The task offloading problem is formulated as a Markov Decision Process(MDP)to minimize computational delay.Task dependencies are modeled using a Directed Acyclic Graph(DAG),and a Graph Convolutional Network(GCN)encoder is employed to extract DAG features as inputs for a Deep Reinforcement Learning(DRL)model.The proposed DRL-based method applies the Proximal Policy Optimization(PPO)algorithm to simultaneously select subtasks and determine their offloading decisions.Experimental evaluations across varying numbers of subtasks confirm the effectiveness of the approach,demonstrating superior performance compared to state-of-the-art solutions. 展开更多
关键词 Task offloading Edge computing Graph neural network Deep reinforcement learning
暂未订购 下载PDF
A Deep Reinforcement Learning-Based Pre-Allocation Mechanism for Efficient Task Offloading in Mobile Edge Computing 认领 引用
6
作者 Chaobin Wang Xianghong Tang +2 位作者 Jianguang Lu Jing Yang Panliang Yuan 《Computers, Materials & Continua》 SCIE EI 2026年第7期1086-1113,共28页
Mobile Edge Computing(MEC)facilitates the rapid response and energy-efficient execution of tasks on mobile devices.However,determining whether and where to offload tasks remains a significant challenge due to the cons... Mobile Edge Computing(MEC)facilitates the rapid response and energy-efficient execution of tasks on mobile devices.However,determining whether and where to offload tasks remains a significant challenge due to the constantly changing character of workloads in MEC environments.To address this issue,this paper proposes PreAlloc-A2C—a deep reinforcement learning actor-critic-based framework that calculates allocation scores by leveraging both task features(task size,required completion time,and waiting time)and server features(queue length and historical workload).This design enables fully distributed task offloading decisions without centralized coordination.Additionally,a Long Short-Term Memory(LSTM)network is integrated to forecast impending server loads,thereby supporting adaptive scheduling.A tailored reward function is also designed to jointly optimize three key performance metrics:task delay,device energy consumption,and task drop rate.Extensive experiments are conducted to evaluate PreAlloc-A2C against five baseline algorithms:Particle Swarm Optimization(PSO),Advantage Actor-Critic(A2C),Deep Q-Network(DQN),Double Deep Q-Network(DDQN),and Dueling Deep Q-Network(Dueling DQN).The results show that PreAlloc-A2C outperforms all baselines,achieving lower latency,reduced energy consumption,and a lower task drop rate. 展开更多
关键词 Mobile edge computing task offloading deep reinforcement learning
暂未订购 下载PDF
Edge computing aileron mechatronics using antiphase hysteresis Schmitt trigger for fast flutter suppression 认领 引用 被引量：1
7
作者 Tangwen Yin Dan Huang Xiaochun Zhang 《Control Theory and Technology》 EI CSCD 2025年第1期153-160,共8页
An aileron is a crucial control surface for rolling.Any jitter or shaking caused by the aileron mechatronics could have catastrophic consequences for the aircraft’s stability,maneuverability,safety,and lifespan.This ... An aileron is a crucial control surface for rolling.Any jitter or shaking caused by the aileron mechatronics could have catastrophic consequences for the aircraft’s stability,maneuverability,safety,and lifespan.This paper presents a robust solution in the form of a fast flutter suppression digital control logic of edge computing aileron mechatronics(ECAM).We have effectively eliminated passive and active oscillating response biases by integrating nonlinear functional parameters and an antiphase hysteresis Schmitt trigger.Our findings demonstrate that self-tuning nonlinear parameters can optimize stability,robustness,and accuracy.At the same time,the antiphase hysteresis Schmitt trigger effectively rejects flutters without the need for collaborative navigation and guidance.Our hardware-in-the-loop simulation results confirm that this approach can eliminate aircraft jitter and shaking while ensuring expected stability and maneuverability.In conclusion,this nonlinear aileron mechatronics with a Schmitt positive feedback mechanism is a highly effective solution for distributed flight control and active flutter rejection. 展开更多
关键词 Aileron Edge computing Flutter suppression Mechatronics Nonlinear hysteresis control Positive feedback
A Secure Task Offloading Scheme for UAV-Assisted MEC with Dynamic User Clustering and Cooperative Jamming: A Method Combining K-Means and SAC (K-SAC) 认领 引用
8
作者 Jiajia Liu Shuchen Pang +7 位作者 Peng Xie Haitao Zhou Chenxi Du Haoran Hu Bo Tang Jianhua Liu Fei Jia Huibing Zhang 《Computers, Materials & Continua》 SCIE EI 2026年第6期1323-1346,共24页
In the unmanned aerial vehicle(UAV)assisted edge computing system,the broadcast characteristics of the UAV signal,the high mobility of the UAV,and the limited airborne energy make the task offloading strategy face cha... In the unmanned aerial vehicle(UAV)assisted edge computing system,the broadcast characteristics of the UAV signal,the high mobility of the UAV,and the limited airborne energy make the task offloading strategy face challenges such as increased risk of information disclosure,limited computing resources,and the trade-off between energy consumption and flight time.To address these issues,we propose a K-means in-depth reinforcement learning algorithm based on Soft Actor-Critic(SAC).The proposed method first leverages the K-means clustering algorithm to determine the optimal deployment of ground jammers based on the final distribution of mobile users.Then,building upon the SAC framework,the Cross-Entropy Method(CEM)global sampling strategy is incorporated into the action output phase to form the K-SAC algorithm.This algorithm aims to maximize system rewards,which holistically balance task offloading delay,energy consumption,and secure offloading rate.Consequently,it jointly optimizes the optimal hovering positions of auxiliary UAVs and the task offloading ratio for each user,leading to an overall performance improvement in system security and efficiency.Finally,compared with current schemes,the system benefits achieved by the proposed scheme were 9.83%higher on average in different computing task sizes,13.67%higher on average in different task complexities,and 14.63%higher on average in different interference powers. 展开更多
关键词 Mobile edge computing(MEC) SAC communication security K-means UAV
暂未订购 下载PDF
Memristor devices for next-generation computing:from performance optimization to application-specific co-design 认领 引用 被引量：1
9
作者 Zhaorui Liu Caifang Gao +5 位作者 Jingbo Yang Zuxin Chen Enlong Li Jun Li Mengjiao Li Jianhua Zhang 《International Journal of Extreme Manufacturing》 SCIE EI CAS CSCD 2026年第1期119-146,共28页
Memristors have emerged as a transformative technology in the realm of electronic devices,offering unique advantages such as fast switching speeds,low power consumption,and the ability to sensor-memory-compute.The app... Memristors have emerged as a transformative technology in the realm of electronic devices,offering unique advantages such as fast switching speeds,low power consumption,and the ability to sensor-memory-compute.The applications span across non-volatile memory,neuromorphic computing,hardware security,and beyond,prompting memristors to become a versatile solution for next-generation computing and data storage systems.Despite enormous potential of memristors,the transition from laboratory prototypes to large-scale applications is challenging in terms of material stability,device reproducibility,and array scalability.This review systematically explores recent advancements in high-performance memristor technologies,focusing on performance enhancement strategies through material engineering,structural design,pulse protocol optimization,and algorithm control.We provide an in-depth analysis of key performance metrics tailored to specific applications,including non-volatile memory,neuromorphic computing,and hardware security.Furthermore,we propose a co-design framework that integrates device-level optimizations with operational-level improvements,aiming to bridge the gap between theoretical models and practical implementations. 展开更多
关键词 memristor performance optimization device design neuromorphic computing
暂未订购 下载PDF
Task Offloading and Edge Computing in IoT-Gaps, Challenges and Future Directions 认领 引用 被引量：1
10
作者 Hitesh Mohapatra 《Computers, Materials & Continua》 SCIE EI 2026年第6期268-296,共29页
This review examines current approaches to real-time decision-making and task optimization in Internet of Things systems through the application of machine learning models deployed at the network edge.Existing literat... This review examines current approaches to real-time decision-making and task optimization in Internet of Things systems through the application of machine learning models deployed at the network edge.Existing literature shows that edge-based distributed intelligence reduces cloud dependency.It addresses transmission latency,device energy use,and bandwidth limits.Recent optimization strategies employ dynamic task offloading mechanisms to determine optimal workload placement across local devices and edge servers without centralized coordination.Empirical findings from the literature indicate performance improvements with latency reductions of approximately 32.8%and energy efficiency gains of 27.4%compared to conventional cloud-centric models.However,critical gaps remain in current methodologies.Most studies focus on static network topologies and do not adequately address load balancing across multiple edge nodes.Security vulnerabilities during task transmission are underexplored,and privacy considerations for sensitive data remain insufficiently integrated into existing frameworks.Task caching strategies and fault tolerance mechanisms require further investigation in highly dynamic environments.The ability of existing approaches to handle large-scale deployments and complex edge-cloud collaborative scenarios has not been thoroughly validated.This review synthesizes current progress while identifying fundamental challenges that must be resolved for practical deployment in time-sensitive applications spanning smart manufacturing,autonomous systems,and healthcare monitoring.Future work should prioritize robust security integration,efficient load distribution,and scalability across heterogeneous edge infrastructures. 展开更多
关键词 Edge computing task offloading deep reinforcement learning mobile edge computing IoT performance optimization methodological rigor assessment
暂未订购 下载PDF
Computing power networks for unmanned aerial vehicles:a hierarchical resources trading market 认领 引用
11
作者 Xiaofei Wang Hui Deng +3 位作者 Chao Qiu Zheyuan Chen Tao Luo Zhao Ming 《Digital Communications and Networks》 SCIE EI CSCD 2026年第4期584-593,共10页
Unmanned Aerial Vehicles(UAVs)are increasingly deployed across military and civilian domains due to their operational flexibility,low maintenance costs,and high mobility.With the growing complexity of UAV applications... Unmanned Aerial Vehicles(UAVs)are increasingly deployed across military and civilian domains due to their operational flexibility,low maintenance costs,and high mobility.With the growing complexity of UAV applications and tasks,robust support from computing power networks is essential.These networks,acting as resource integration paradigms,furnish UAVs with pooled resources to tackle extensive computational demands.In this paper,we develop a framework for trading computing power resources,modeling the transaction process through a three-stage Stackelberg game to facilitate sequential decision-making.We theoretically demonstrate the existence of a Nash equilibrium and introduce a Dynamic Game Reinforcement algorithm to identify optimal strategies.Our experimental results affirm the framework's efficacy and the superior performance of our algorithm.Additionally,we explore how variables like UAV quantity and network congestion influence the market dynamics of the computing power network. 展开更多
关键词 UAVs Cloud computing Computing power network Resource trading Stackelberg game
暂未订购 下载PDF
Back-gate-tuned organic electrochemical transistor with temporal dynamic modulation for reservoir computing 认领 引用
12
作者 Qian Xu Jie Qiu +6 位作者 Mengyang Liu Dongzi Yang Tingpan Lan Jie Cao Yingfen Wei Hao Jiang Ming Wang 《Journal of Semiconductors》 EI CAS CSCD 2026年第1期118-123,共6页
Organic electrochemical transistor(OECT)devices demonstrate great promising potential for reservoir computing(RC)systems,but their lack of tunable dynamic characteristics limits their application in multi-temporal sca... Organic electrochemical transistor(OECT)devices demonstrate great promising potential for reservoir computing(RC)systems,but their lack of tunable dynamic characteristics limits their application in multi-temporal scale tasks.In this study,we report an OECT-based neuromorphic device with tunable relaxation time(τ)by introducing an additional vertical back-gate electrode into a planar structure.The dual-gate design enablesτreconfiguration from 93 to 541 ms.The tunable relaxation behaviors can be attributed to the combined effects of planar-gate induced electrochemical doping and back-gateinduced electrostatic coupling,as verified by electrochemical impedance spectroscopy analysis.Furthermore,we used theτ-tunable OECT devices as physical reservoirs in the RC system for intelligent driving trajectory prediction,achieving a significant improvement in prediction accuracy from below 69%to 99%.The results demonstrate that theτ-tunable OECT shows a promising candidate for multi-temporal scale neuromorphic computing applications. 展开更多
关键词 neuromorphic computing reservoir computing OECT tunable dynamics trajectory prediction
暂未订购 下载PDF
The three-dimensional meshfree numerical manifold method based on parallel computing 认领 引用
13
作者 Keqin Zhang Wei Wu +2 位作者 Danfeng Zhang Yanfei Kang Hehua Zhu 《Acta Mechanica Sinica》 SCIE EI CAS CSCD 2026年第2期360-371,共12页
The numerical manifold method,extensively utilized in numerical computations,faces significant challenges in generating complex manifold elements,particularly for three-dimensional applications.To overcome this challe... The numerical manifold method,extensively utilized in numerical computations,faces significant challenges in generating complex manifold elements,particularly for three-dimensional applications.To overcome this challenge,the meshfree numerical manifold method is developed by integrating the moving least-squares method into the numerical manifold method,effectively bypassing the need for meshing complex geometric objects.However,the implementation of the moving least-squares method introduces computational efficiency issues.To mitigate these,parallel computing methods have been incorporated,resulting in a tenfold increase in the speed of assembling the stiffness matrix with central processing unit parallelism,and a twentyfold increase with graphics processing unit parallelism.The static mechanical system equations for the meshfree numerical manifold method are derived using the Galerkin method.The method’s effectiveness and accuracy are then validated through a series of numerical experiments.The experiments demonstrated that the meshfree numerical manifold method achieves a high precision with minimal nodes and integration points.Additionally,positioning nodes outside the domain significantly improves computational accuracy at the boundaries. 展开更多
关键词 Meshfree numerical manifold method Three-dimensional computation Parallel computation Elastostatics Moving least-squares
暂未订购 下载PDF
Large-scale integrated photonic accelerators for ultralow-latency and universal AI computing 认领 引用
14
作者 Xiangyan Meng Junshen Li +4 位作者 Kangwei Fei Yu Wang Wei Li Nuannuan Shi Ming Li 《Journal of Semiconductors》 EI CAS CSCD 2026年第6期12-15,共4页
Integrated silicon photonics has emerged as a transformative technology for post-Moore’s law computing,offering intrinsic advantages of high bandwidth,ultralow latency and low energy consumption that far exceed tradi... Integrated silicon photonics has emerged as a transformative technology for post-Moore’s law computing,offering intrinsic advantages of high bandwidth,ultralow latency and low energy consumption that far exceed traditional electronic computing architectures[1−4].As artificial intelligence(AI)models continue to grow in complexity and scale,the demand for high-speed,energy-efficient computing has spurred intensive research into photonic computing as a promising alternative to electronic accelerators[5−7].Matrix multiply−accumulate(MAC)operations,the core of deep learning and combinatorial optimization algorithms,are particularly amenable to photonic implementation,as light enables parallel multiplication and accumulation with minimal data movement[8,9].However,the practical application of photonic computing has long been hindered by critical challenges including large-scale integration of photonic components,electro-optical co-packaging,guaranteed computation accuracy of analog photonic systems,and compatibility with mainstream AI models and algorithms[10,11]. 展开更多
关键词 photonic computing integrated silicon photonics electronic computing ultralow latency matrix multiply accumulate analog photonic systems silicon photonics electronic accelerators matrix
暂未订购 下载PDF
Computing-centric computing-in-memory and memory-centric in-/near-memory computing for DNNs and transformer based LLMs 认领 引用
15
作者 Xin Si Xing Wang Jun Yang 《Journal of Semiconductors》 EI CAS CSCD 2026年第7期7-11,共5页
Introduction.With the rapid development of transformer-based large language models(LLMs)and deep neural networks(DNNs),the demand for both high computational throughput and massive memory capacity has grown exponentia... Introduction.With the rapid development of transformer-based large language models(LLMs)and deep neural networks(DNNs),the demand for both high computational throughput and massive memory capacity has grown exponentially[1-4].In response,the 2D/3D hybrid integration of computing-centric computing-in-memory(CIM)and memory-centric in-ear-memory computing(INMC)circuits has emerged as a transformative technology.Unlike conventional von Neumann architectures,these memory-computing hybrid designs offer systematic advantages including high energy efficiency,high memory bandwidth,and sufficient on-device memory capacity[1-13]. 展开更多
关键词 von neumann architecturesthese near memory computing transformer based large language models large language models llms memory computing deep neural networks dnns memory centric computing centric
暂未订购 下载PDF
A low-thermal-budget MOSFET-based reservoir computing for temporal data classification 认领 引用
16
作者 Yanqing Li Feixiong Wang +5 位作者 Heyi Huang Yadong Zhang Xiangpeng Liang Shuang Liu Jianshi Tang Huaxiang Yin 《Journal of Semiconductors》 EI CAS CSCD 2026年第1期42-48,共7页
Neuromorphic devices have garnered significant attention as potential building blocks for energy-efficient hardware systems owing to their capacity to emulate the computational efficiency of the brain.In this regard,r... Neuromorphic devices have garnered significant attention as potential building blocks for energy-efficient hardware systems owing to their capacity to emulate the computational efficiency of the brain.In this regard,reservoir computing(RC)framework,which leverages straightforward training methods and efficient temporal signal processing,has emerged as a promising scheme.While various physical reservoir devices,including ferroelectric,optoelectronic,and memristor-based systems,have been demonstrated,many still face challenges related to compatibility with mainstream complementary metal oxide semiconductor(CMOS)integration processes.This study introduced a silicon-based schottky barrier metal-oxide-semiconductor field effect transistor(SB-MOSFET),which was fabricated under low thermal budget and compatible with back-end-of-line(BEOL).The device demonstrated short-term memory characteristics,facilitated by the modulation of schottky barriers and charge trapping.Utilizing these characteristics,a RC system for temporal data processing was constructed,and its performance was validated in a 5×4 digital classification task,achieving an accuracy exceeding 98%after 50 training epochs.Furthermore,the system successfully processed temporal signal in waveform classification and prediction tasks using time-division multiplexing.Overall,the SB-MOSFET's high compatibility with CMOS technology provides substantial advantages for large-scale integration,enabling the development of energy-efficient reservoir computing hardware. 展开更多
关键词 schottky barrier MOSFET back-end-of-line integration reservoir computing
暂未订购 下载PDF
Carbon nanotube-based bio-inspired neuron systems via cascaded thin-film transistor-driven light emitting diodes and optoelectronic synaptic transistors for neuromorphic computing 认领 引用
17
作者 Jiaqi Li Lingzhi Wu +6 位作者 Jing Xu Min Li Mingnan Chen Chengyong Xu Shuangshuang Shao Manman Luo Jianwen Zhao 《International Journal of Extreme Manufacturing》 SCIE EI CAS CSCD 2026年第2期756-770,共15页
The development of bio-inspired neural systems has emerged as a transformative approach to overcome the limitations of von Neumann architecture,replicating the remarkable energy efficiency and unified sensory-processi... The development of bio-inspired neural systems has emerged as a transformative approach to overcome the limitations of von Neumann architecture,replicating the remarkable energy efficiency and unified sensory-processing capabilities of biological neurons.In this work,we present a monolithic neuromorphic platform utilizing cascaded single-walled carbon nanotube thin-film transistors(SWCNT TFTs)that integrate Mini-light-emitting diodes(Mini-LEDs)with optoelectronic synaptic transistors,achieving synergistic optoelectronic integration.The SWCNT TFTs exhibit dual functionality:(1)as highly stable active-matrix drivers(>1000 operational cycles)enabling precise Mini-LED grayscale modulation,and(2)as efficient optoelectronic synaptic devices.Fabricated at wafer-scale with micrometer feature sizes,these devices demonstrate exceptional performance metrics,including low operating voltages(±1 V),high on/off ratios(106),near-ideal subthreshold swing(78 mV·dec-1),and precise Mini-LED current regulation(10-8A-10-4A)under 25 Hz pulsed gate operation.The optoelectronic synaptic devices based on organic-semiconductor heterojunction formed between poly(3,3”’-didodecyl quaterthiophene)(PQT-12)and semiconducting SWCNTs enable broadband photoresponses(365 nm-710 nm)through efficient charge transport,driven by TFT-controlled Mini-LED pulses.The implemented bio-inspired visual system successfully emulates fundamental synaptic functionalities,exhibiting excitatory postsynaptic currents(EPSC),short-term potentiation(STP),and long-term potentiation(LTP).Notably,we demonstrate system-level functionality through a five-layer convolutional neural network,achieving 92.02%accuracy on MNIST classification,while the monolithic integration establishes a biomimetic closed-loop“electrical-optical-electrical”pathway that faithfully simulates complete biological synaptic operation.This pioneering cascade of electronic,photonic,and optoelectronic components represents a significant advancement toward high-density,energy-efficient neuromorphic computing. 展开更多
关键词 carbon nanotube thin-film transistor optoelectronic synaptic transistors bio-inspired neuron system neuromorphic computing
暂未订购 下载PDF
Underlying Framework of All-optical Controlled Synaptic Devices for Neuromorphic Computing 认领 引用
18
作者 Dunan Hu Ruqi Yang +1 位作者 Zhizhen Ye Jianguo Lu 《Nano-Micro Letters》 SCIE EI CAS CSCD 2026年第9期685-755,共71页
The rapid expansion of artificial intelligence has led to significant challenges in energy consumption and computational efficiency.To address these issues,the exploration and development of all-optical controlled(AOC... The rapid expansion of artificial intelligence has led to significant challenges in energy consumption and computational efficiency.To address these issues,the exploration and development of all-optical controlled(AOC)synaptic devices represents a promising leap forward in neuromorphic computing,offering potential solutions to the inherent limitations of traditional von Neumann architectures.AOC synaptic devices,utilizing exclusively optical signals to emulate bidirectional modulation of synaptic weights,bypass the complexity and additional energy costs associated with conventional electrical or electro-optical hybrid signals.This review articulates the underlying framework and fundamental motivations for studying AOC synapses,while systematically reviewing current research progress.We particularly highlight the synergistic relationships among physical mechanisms,material behaviors,and device architectures,as well as neuromorphic computing based on optical writing and optical erasing of information.By systematically interpreting these multidimensional correlations,we propose scalable and reproducible strategies for device design.This work will certainly herald a substantial direction of AOC synapses,providing an ideal platform for exploring neuromorphic computing for artificial intelligence. 展开更多
关键词 All-optical control Artificial synapse Device mechanisms Design framework Neuromorphic computing
暂未订购 下载PDF
In-Sensor Reservoir Computing Employing Reconfigurable Optoelectronic Transistors for Multi-Task Learning 认领 引用
19
作者 Shanshan Jiang Hainan Zhang +4 位作者 Kesheng Wang Shuo Cheng Can Fu Huanhuan Wei Gang He 《Rare Metals》 SCIE EI CAS CSCD 2026年第4期629-639,共11页
The edge deployment of artificial intelligence has driven the exploitation of compact,energy-efficient information processing systems that integrate sensing,memory,and multi-task processing functions.However,conventio... The edge deployment of artificial intelligence has driven the exploitation of compact,energy-efficient information processing systems that integrate sensing,memory,and multi-task processing functions.However,conventional vision systems suffer from significant energyime overhead,extra hardware costs,and an unaffordable algorithm.Herein,we demonstrate an in-sensor computing system employing reconfigurable optoelectronic transistors(ROETs)for multi-task learning.These transistors exhibit reconfigurable volatile and nonvolatile characteristics under both optical and electrical stimuli.Capitalizing on this reconfigurability,we establish an in-sensor reservoir computing(RC)system operating in multi-signal modes:volatile dynamics function as the reservoir,whereas nonvolatile properties configure the readout layer.The abundant optoelectronic reservoir states display exceptional feature separability and prolonged stability in the ambient atmosphere.Such a reliable RC system successfully achieves multi-task processing of images.Notably,under the optoelectronic coordination mode,it effectively alleviates feature degradation while sustaining consistently high recognition accuracy.Furthermore,the system exhibits remarkable dynamic information processing capabilities,achieving recognition accuracies of 89.02%for dynamic gestures and 96.04%for moving vehicles recognition,respectively.Supplemental functionalities,including light adaptation and image sharpening,are also implemented.This work presents a configurable multimodal platform featuring a flexible in-sensor reservoir computing architecture,providing a potential solution for efficient multi-task processing. 展开更多
关键词 in-sensor reservoir computing multi-task learning neuromorphic applications optoelectronic transistors reconfigurable devices
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 250 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈