Neuromorphic computing extends beyond sequential processing modalities and outperforms traditional von Neumann architectures in implementing more complicated tasks,e.g.,pattern processing,image recognition,and decisio...Neuromorphic computing extends beyond sequential processing modalities and outperforms traditional von Neumann architectures in implementing more complicated tasks,e.g.,pattern processing,image recognition,and decision making.It features parallel interconnected neural networks,high fault tolerance,robustness,autonomous learning capability,and ultralow energy dissipation.The algorithms of artificial neural network(ANN)have also been widely used because of their facile self-organization and self-learning capabilities,which mimic those of the human brain.To some extent,ANN reflects several basic functions of the human brain and can be efficiently integrated into neuromorphic devices to perform neuromorphic computations.This review highlights recent advances in neuromorphic devices assisted by machine learning algorithms.First,the basic structure of simple neuron models inspired by biological neurons and the information processing in simple neural networks are particularly discussed.Second,the fabrication and research progress of neuromorphic devices are presented regarding to materials and structures.Furthermore,the fabrication of neuromorphic devices,including stand-alone neuromorphic devices,neuromorphic device arrays,and integrated neuromorphic systems,is discussed and demonstrated with reference to some respective studies.The applications of neuromorphic devices assisted by machine learning algorithms in different fields are categorized and investigated.Finally,perspectives,suggestions,and potential solutions to the current challenges of neuromorphic devices are provided.展开更多
Neuromorphic devices,inspired by the intricate architecture of the human brain,have garnered recognition for their prodigious computational speed and sophisticated parallel computing capabilities.Vision,the primary mo...Neuromorphic devices,inspired by the intricate architecture of the human brain,have garnered recognition for their prodigious computational speed and sophisticated parallel computing capabilities.Vision,the primary mode of external information acquisition in living organisms,has garnered substantial scholarly interest.Notwithstanding numerous studies simulating the retina through optical synapses,their applications remain circumscribed to single-mode perception.Moreover,the pivotal role of temperature,a fundamental regulator of biological activities,has regrettably been relegated to the periphery.To address these limitations,we proffer a neuromorphic device endowed with multimodal perception,grounded in the principles of light-modulated semiconductors.This device seamlessly accomplishes dynamic hybrid visual and thermal multimodal perception,featuring temperature-dependent paired pulse facilitation properties and adaptive storage.Crucially,our meticulous examination of transfer curves,capacitance–voltage(C–V)tests,and noise measurements provides insights into interface and bulk defects,elucidating the physical mechanisms underlying adaptive storage and other functionalities.Additionally,the device demonstrates a variety of synaptic functionalities,including filtering properties,Ebbinghaus curves,and memory applications in image recognition.Surprisingly,the digital recognition rate achieves a remarkable value of 98.8%.展开更多
Neuromorphic computing is a brain-inspired computing paradigm that aims to construct efficient,low-power,and adaptive computing systems by emulating the information processing mechanisms of biological neural systems.A...Neuromorphic computing is a brain-inspired computing paradigm that aims to construct efficient,low-power,and adaptive computing systems by emulating the information processing mechanisms of biological neural systems.At the core of neuromorphic computing are neuromorphic devices that mimic the functions and dynamics of neurons and synapses,enabling the hardware implementation of artificial neural networks.Various types of neuromorphic devices have been proposed based on different physical mechanisms such as resistive switching devices and electric-double-layer transistors.These devices have demonstrated a range of neuromorphic functions such as multistate storage,spike-timing-dependent plasticity,dynamic filtering,etc.To achieve high performance neuromorphic computing systems,it is essential to fabricate neuromorphic devices compatible with the complementary metal oxide semiconductor(CMOS)manufacturing process.This improves the device’s reliability and stability and is favorable for achieving neuromorphic chips with higher integration density and low power consumption.This review summarizes CMOS-compatible neuromorphic devices and discusses their emulation of synaptic and neuronal functions as well as their applications in neuromorphic perception and computing.We highlight challenges and opportunities for further development of CMOS-compatible neuromorphic devices and systems.展开更多
Rapid developments in artificial intelligence trigger demands for perception and learning of external environments through visual perception systems.Neuromorphic devices and integrated system with photosensing and res...Rapid developments in artificial intelligence trigger demands for perception and learning of external environments through visual perception systems.Neuromorphic devices and integrated system with photosensing and response functions can be constructed to mimic complex biological visual sensing behaviors.Here,recent progresses on optoelectronic neuromorphic memristors and optoelectronic neuromorphic transistors are briefly reviewed.A variety of visual synaptic functions stimulated on optoelectronic neuromorphic devices are discussed,including light-triggered short-term plasticities,long-term plasticities,and neural facilitation.These optoelectronic neuromorphic devices can also mimic human visual perception,information processing,and cognition.The optoelectronic neuromorphic devices that simulate biological visual perception functions will have potential application prospects in areas such as bionic neurological optoelectronic systems and intelligent robots.展开更多
With the arrival of the era of artificial intelligence(AI)and big data,the explosive growth of data has raised higher demands on computer hardware and systems.Neuromorphic techniques inspired by biological nervous sys...With the arrival of the era of artificial intelligence(AI)and big data,the explosive growth of data has raised higher demands on computer hardware and systems.Neuromorphic techniques inspired by biological nervous systems are expected to be one of the approaches to breaking the von Neumann bottleneck.Piezotronic neuromorphic devices modulate electrical transport characteristics by piezopotential and directly associate external mechanical motion with electrical output signals in an active manner,with the capability to sense/store/process information of external stimuli.In this review,we have presented the piezotronic neuromorphic devices(which are classified into strain-gated piezotronic transistors and piezoelectric nanogenerator-gated field effect transistors based on device structure)and discussed their operating mechanisms and related manufacture techniques.Secondly,we summarized the research progress of piezotronic neuromorphic devices in recent years and provided a detailed discussion on multifunctional applications,including bionic sensing,information storage,logic computing,and electrical/optical artificial synapses.Finally,in the context of future development,challenges,and perspectives,we have discussed how to modulate novel neuromorphic devices with piezotronic effects more effectively.It is believed that the piezotronic neuromorphic devices have great potential for the next generation of interactive sensation/memory/computation to facilitate the development of the Internet of Things,AI,biomedical engineering,etc.展开更多
Traditional von Neumann computing,with physical separation of memory and processing units,cannot satisfy the development of artificial intelligence and cloud computing.Neuromorphic computing,inspired by the human brai...Traditional von Neumann computing,with physical separation of memory and processing units,cannot satisfy the development of artificial intelligence and cloud computing.Neuromorphic computing,inspired by the human brain,has drawn much attention.All-optical neuromorphic(AON)devices employ optical signals as information carriers and leverage the neuromorphic functions to implement fast operation speed,low energy consumption,and high bandwidth of neuromorphic computing.Here,we discuss the recent progress in AON devices,including materials,device performance,working mechanisms,and applications.Moreover,the advantages and limitations of AON are presented and discussed.Finally,the perspective of AON devices points out the future research direction of neuromorphic computing.展开更多
Multi-sensory neuromorphic devices(MND)have broad potential in overcoming the structural bottleneck of von Neumann in the era of big data.However,the current multisensory artificial neuromorphic system is mainly based...Multi-sensory neuromorphic devices(MND)have broad potential in overcoming the structural bottleneck of von Neumann in the era of big data.However,the current multisensory artificial neuromorphic system is mainly based on unitary nonvolatile memory or volatile synaptic devices without intrinsic thermal sensitivity,which limits the range of biological multisensory perception and the flexibility and computational efficiency of the neural morphological computing system.Here,a temperature-dependent memory/synaptic hybrid artificial neuromorphic device based on floating gate phototransistors(FGT)is fabricated.The CsPbBr_(3)/TiO_(2)core–shell nanocrystals(NCs)prepared by in-situ pre-protection low-temperature solvothermal method were used as the photosensitive layer.The device exhibits remarkable multi-level visual memory with a large memory window of 59.6 V at room temperature.Surprisingly,when the temperature varies from 20 to 120℃back and forth,the device can switch between nonvolatile memory and volatile synaptic device with reconfigurable and reversible behaviors,which contributes to the efficient visual/thermal fusion perception.This work expands the sensory range of multisensory devices and promotes the development of memory and neuromorphic devices based on organic field-effect transistors(OFET).展开更多
Neuromorphic devices have shown great potential in simulating the function of biological neurons due to their efficient parallel information processing and low energy consumption.MXene-Ti_(3)C_(2)T_(x),an emerging two...Neuromorphic devices have shown great potential in simulating the function of biological neurons due to their efficient parallel information processing and low energy consumption.MXene-Ti_(3)C_(2)T_(x),an emerging twodimensional material,stands out as an ideal candidate for fabricating neuromorphic devices.Its exceptional electrical performance and robust mechanical properties make it an ideal choice for this purpose.This review aims to uncover the advantages and properties of MXene-Ti_(3)C_(2)T_(x)in neuromorphic devices and to promote its further development.Firstly,we categorize several core physical mechanisms present in MXene-Ti_(3)C_(2)T_(x)neuromorphic devices and summarize in detail the reasons for their formation.Then,this work systematically summarizes and classifies advanced techniques for the three main optimization pathways of MXene-Ti_(3)C_(2)T_(x),such as doping engineering,interface engineering,and structural engineering.Significantly,this work highlights innovative applications of MXene-Ti_(3)C_(2)T_(x)neuromorphic devices in cutting-edge computing paradigms,particularly near-sensor computing and in-sensor computing.Finally,this review carefully compiles a table that integrates almost all research results involving MXene-Ti_(3)C_(2)T_(x)neuromorphic devices and discusses the challenges,development prospects,and feasibility of MXene-Ti_(3)C_(2)T_(x)-based neuromorphic devices in practical applications,aiming to lay a solid theoretical foundation and provide technical support for further exploration and application of MXene-Ti_(3)C_(2)T_(x)in the field of neuromorphic devices.展开更多
Two-dimensional (2D) materials have attracted significant attention as resistive switching materials for two-terminal non-volatile memory devices, often referred to as memristors, due to their potential for achieving ...Two-dimensional (2D) materials have attracted significant attention as resistive switching materials for two-terminal non-volatile memory devices, often referred to as memristors, due to their potential for achieving fast switching speeds and low power consumption. Their excellent gate tunability in electronic properties also enables hybrid devices combining the functionality of memory devices and transistors, with the possibility of realizing large-scale memristive crossbar arrays with high integration density. To facilitate the use of 2D materials in practical memristor applications, scalable synthesis of 2D materials with high electronic quality is critical. In addition, low-temperature integration for complementary metal oxide semiconductor (CMOS) back-end-of-line (BEOL) integration is important for embedded memory applications. Solution-based exfoliation has been actively explored as a facile, cost-effective method for the mass production and low-temperature integration of 2D materials. However, the films produced from the resulting 2D nanosheet dispersions exhibited poor electrical properties in the early stages of research, thereby hindering their use in electronic devices. Recent progress in the exfoliation process and post-processing has led to significant improvements in the electronic performance of solution-processed 2D materials, driving increased adoption of these materials in memristor research. In this review article, we provide a thorough overview of the progress and current status of memristive devices utilizing solution-processed 2D resistive switching layers. We begin by introducing the electrical characteristics and resistive switching mechanisms of memristors fabricated with conventional materials to lay the groundwork for understanding memristive behavior in 2D materials. Representative solution-based exfoliation and film formation techniques are also introduced, emphasizing the benefits of these approaches for obtaining scalable 2D material films compared to conventional methods such as mechanical exfoliation and chemical vapor deposition. Finally, we explore the electrical characteristics, resistive switching mechanisms, and applications of solution-processed 2D memristive devices, discussing their advantages and remaining challenges.展开更多
Robots are widely used,providing significant convenience in daily life and production.With the rapid development of artificial intelligence and neuromorphic computing in recent years,the realization of more intelligen...Robots are widely used,providing significant convenience in daily life and production.With the rapid development of artificial intelligence and neuromorphic computing in recent years,the realization of more intelligent robots through a pro-found intersection of neuroscience and robotics has received much attention.Neuromorphic circuits based on memristors used to construct hardware neural networks have proved to be a promising solution of shattering traditional control limita-tions in the field of robot control,showcasing characteristics that enhance robot intelligence,speed,and energy efficiency.Start-ing with introducing the working mechanism of memristors and peripheral circuit design,this review gives a comprehensive analysis on the biomimetic information processing and biomimetic driving operations achieved through the utilization of neuro-morphic circuits in brain-like control.Four hardware neural network approaches,including digital-analog hybrid circuit design,novel device structure design,multi-regulation mechanism,and crossbar array,are summarized,which can well simulate the motor decision-making mechanism,multi-information integration and parallel control of brain at the hardware level.It will be definitely conductive to promote the application of memristor-based neuromorphic circuits in areas such as intelligent robotics,artificial intelligence,and neural computing.Finally,a conclusion and future prospects are discussed.展开更多
Next-generation artificial tactile systems demand seamless integration with neuromorphic architectures to support on-edge computation and high-fidelity sensory signal processing.Despite significant advancements,curren...Next-generation artificial tactile systems demand seamless integration with neuromorphic architectures to support on-edge computation and high-fidelity sensory signal processing.Despite significant advancements,current research remains predominantly focused on optimizing individual sensor elements,and systems utilizing single neuromorphic components encounter inherent limitations in enhancing overall functionality.Here,we present a vertically integrated in-sensor processing platform,which combines a three-dimensional antiferroelectric field-effect transistor(AFEFET)device with an aluminum nitride(AlN)piezoelectric sensor.展开更多
Rapid development of artificial intelligence requires the implementation of hardware systems with bioinspired parallel information processing and presentation and energy efficiency.Electrolyte-gated organic transistor...Rapid development of artificial intelligence requires the implementation of hardware systems with bioinspired parallel information processing and presentation and energy efficiency.Electrolyte-gated organic transistors(EGOTs)offer significant advantages as neuromorphic devices due to their ultra-low operation voltages,minimal hardwired connectivity,and similar operation environment as electrophysiology.Meanwhile,ionic–electronic coupling and the relatively low elastic moduli of organic channel materials make EGOTs suitable for interfacing with biology.This review presents an overview of the device architectures based on organic electrochemical transistors and organic field-effect transistors.Furthermore,we review the requirements of low energy consumption and tunable synaptic plasticity of EGOTs in emulating biological synapses and how they are affected by the organic materials,electrolyte,architecture,and operation mechanism.In addition,we summarize the basic operation principle of biological sensory systems and the recent progress of EGOTs as a building block in artificial systems.Finally,the current challenges and future development of the organic neuromorphic devices are discussed.展开更多
Multisensory integration allows biological organisms to merge information from various sensory modalities,enhancing perception,decision-making,and adaptability in complex environments.This process,involving specialize...Multisensory integration allows biological organisms to merge information from various sensory modalities,enhancing perception,decision-making,and adaptability in complex environments.This process,involving specialized cortical and subcortical areas,reduces uncertainty,speeds up responses,enriches perception,and supports adaptive behaviors.Recent findings reveal that even primary sensory cortices contribute to multisensory processing,further boosting adaptability and decisionmaking.Inspired by these natural capabilities,researchers aim to develop artificial systems replicating biological sensory integration to address challenges in robotics,artificial intelligence,and big data.Current artificial systems,often reliant on single-modal perception,struggle in dynamic environments due to their limited adaptability.Advances in materials,device architectures,and neuromorphic technologies,such as memristor-and transistor-based neurons,are enabling the development of multimodal systems with enhanced efficiency,flexibility,and functionality.This review explores strategies to overcome single-modal limitations,focusing on synchronization,fusion,and deep interpretation of sensory data.Future directions emphasize improving integration density,novel device designs,and adaptable mechanisms.Multimodal systems hold promise to revolutionize artificial perception,narrowing the gap between biological systems and intelligent technologies.展开更多
Current-driven spintronic artificial neural networks(ANNs) hold great promise for image recognition but are limited by excessive power consumption.Surface acoustic waves(SAWs) have recently emerged as a disruptive alt...Current-driven spintronic artificial neural networks(ANNs) hold great promise for image recognition but are limited by excessive power consumption.Surface acoustic waves(SAWs) have recently emerged as a disruptive alternative,offering ultralow-power control over magnetization through the magnetoelastic and acoustothermal effects.In this work,for the first time,we demonstrate a SAW-driven neuromorphic computing paradigm utilizing FeRh magnetic phase transitions,achieving both ReLU neuron activation and robust synaptic plasticity.Notably,the power density of our neuromorphic devices is reduced by an order of magnitude compared to that of conventional spintronic-based devices,enabling power-efficient image recognition with an accuracy exceeding 91%.We also demonstrate that ANNs implemented with our neuromorphic devices can precisely and autonomously assess left ventricular ejection fraction,a key clinical metric for evaluating cardiac function.Our findings establish SAWs as a transformative enabler for next-generation neuromorphic computing,paving the way for energy-efficient,high-precision artificial intelligence in both advanced image processing and medical diagnostics.展开更多
Nowadays, the soar of photovoltaic performance of perovskite solar cells has set off a fever in the study of metal halide perovskite materials. The excellent optoelectronic properties and defect tolerance feature allo...Nowadays, the soar of photovoltaic performance of perovskite solar cells has set off a fever in the study of metal halide perovskite materials. The excellent optoelectronic properties and defect tolerance feature allow metal halide perovskite to be employed in a wide variety of applications. This article provides a holistic review over the current progress and future prospects of metal halide perovskite materials in representative promising applications, including traditional optoelectronic devices(solar cells, light-emitting diodes, photodetectors, lasers), and cutting-edge technologies in terms of neuromorphic devices(artificial synapses and memristors) and pressure-induced emission. This review highlights the fundamentals, the current progress and the remaining challenges for each application, aiming to provide a comprehensive overview of the development status and a navigation of future research for metal halide perovskite materials and devices.展开更多
The advent of the Internet of Things(IoT)era has significantly accelerated advancements in neuromorphic computing research.Triboelectric nanogenerators(TENGs)exhibit dual functionality as both energy harvesters and sy...The advent of the Internet of Things(IoT)era has significantly accelerated advancements in neuromorphic computing research.Triboelectric nanogenerators(TENGs)exhibit dual functionality as both energy harvesters and synaptic simulators,facilitated by their inherent mechanoelectrical transduction properties and seamless circuit integration capabilities.In this work,we presented a vertically contact-separated paper-based artificial synaptic device employing TENG technology.The fabricated device successfully replicates fundamental synaptic behaviors,including paired-pulse facilitation(PPF),high-pass filtering characteristics,and spatiotemporal dynamic logic operations.Through optimized circuit configurations,we achieved elementary“NOT”logic gate using single devices,while implementing“AND/NAND”logic gates and“OR/NOR”logic gates operations through two-and three-device assemblies,respectively.Capitalizing on the mechanical flexibility and lightweight of paper substrates,we further developed a trilayer artificial synaptic architecture that mimics hierarchical neural information processing.This mechanoelectrical coupling approach establishes a novel paradigm for flexible neuromorphic systems,demonstrating exceptional potential for environmentally interactive robotics and adaptive wearable prosthetics.展开更多
Drawing inspiration from the human visual system’s exceptional capabilities in information processing and memory retention,optoelectronic neuromorphic devices have been considered a cutting-edge solution to mimic the...Drawing inspiration from the human visual system’s exceptional capabilities in information processing and memory retention,optoelectronic neuromorphic devices have been considered a cutting-edge solution to mimic these key functions.These devices,particularly optoelectronic memristors,promise to revolutionize neuromorphic computing and visual biomimetic functions,holding significant potential to surpass the traditional von Neumann architecture.Herein,an optoelectronic memristor engineered from a MoS_(2)/WO_(3)heterojunction is developed and integrated with optoelectronic synapses and optical perception capabilities.The device exhibits short/long-term synaptic plasticity under electrical and optical stimuli,effectively mimicking short/long-term memory and“learning-forgetting-relearning”.Leveraging its optical synaptic characteristics,the device successfully simulates complex synaptic behaviors,including Pavlovian conditioning,enabling visual associative learning similar to the biological brain.Through coordinated optoelectronic modulation of long-term potentiation/depression for synaptic weight,the system achieves 98.4%classification accuracy on the Modified National Institute of Standards and Technology(MNIST)handwritten digit recognition task.Moreover,a 4×4 optoelectronic memristor array demonstrates stable visual perception and memory functions under four distinct optical stimuli,facilitating adjustable image memory properties across different light wavelengths.This research advances the application of optoelectronic memristors in neuromorphic computing and bionic visual systems.展开更多
The modern medical field faces two critical challenges:the dramatic increase in data complexity and the explosive growth in data size.Especially in current research,medical diagnostic,and data processing devices relyi...The modern medical field faces two critical challenges:the dramatic increase in data complexity and the explosive growth in data size.Especially in current research,medical diagnostic,and data processing devices relying on traditional computer architecture are increasingly showing limitations when faced with dynamic temporal and spatial processing requirements,as well as high-dimensional data processing tasks.Neuromorphic devices provide a new way for biomedical data processing due to their low energy consumption and high dynamic information processing capabilities.This paper aims to reveal the advantages of neuromorphic devices in biomedical applications.First,this review emphasizes the urgent need of biomedical engineering for diversify clinical diagnostic techniques.Secondly,the feasibility of the application in biomedical engineering is demonstrated by reviewing the historical development of neuromorphic devices from basic modeling to multimodal signal processing.In addition,this paper demonstrates the great potential of neuromorphic chips for application in the fields of biosensing technology,medical image processing and generation,rehabilitation medical engineering,and brain-computer interfaces.Finally,this review provides the pathways for constructing standardized experimental protocols using biocompatible technologies,personalized treatment strategies,and systematic clinical validation.In summary,neuromorphic devices will drive technological innovation in the biomedical field and make significant contributions to life health.展开更多
Scaling of complementary metal-oxide-semiconductor technology nodes using conventional semiconducting materials is slowing down.The development of semiconductor technology with new materials and new concepts has becom...Scaling of complementary metal-oxide-semiconductor technology nodes using conventional semiconducting materials is slowing down.The development of semiconductor technology with new materials and new concepts has become an important focus of scientific and industrial research.In recent years,emerging ambipolar two-dimensional(2D)materials-based reconfigurable devices have shown their potential in high-integration,multifunctional circuits and have begun to attract the attention of researchers.Here,we summarize the latest progress in the field concerning ambipolar 2D materials-based reconfigurable devices.Firstly,we introduce the basic properties and preparation methods of ambipolar 2D materials.Secondly,we discuss the latest applications of reconfigurable devices based on ambipolar 2D materials.Furthermore,we also introduce the current research status of ambipolar material devices in large-scale integration.Finally,we analyze the challenges faced during the development of ambipolar 2D materials-based reconfigurable devices and provide prospects for their future development.展开更多
Emulating brain functionality with neuromorphic devices is an emerging field of research.It is extensively considered as the first step to overcome the limitations of conventional von Neumann systems and build artific...Emulating brain functionality with neuromorphic devices is an emerging field of research.It is extensively considered as the first step to overcome the limitations of conventional von Neumann systems and build artificial intelligent systems.Cur-rently,most neuromorphic transistors are manufactured on rigid substrates,which are difficult to bend and cannot closely fit soft human skin,limiting their appliction scope.The emergence and evolution of flexible electronic devices address a plethora of application and scenario demands.Particularly,the introduction of flexible neuromorphic transistors injects fresh vitality into neuromorphic computing and perception,symbolizing a significant step towards overcoming the limitations of conventional computational models and fostering the development of more intelligent wearable devices.Herein,the recent developments in felxible neuromorphic transistors are summarized and their applications in neuromorphic computing and artificial perception systems are highlighted.The future prospects and challenges of felxible neuromorphic transistors are also discussed.We believe developments in felxible neuromorphic transistors will shed light on future advances in wearable artificial intelligent systems,humanoid robotics and neural repair technology.展开更多
基金financially supported by the National Natural Science Foundation of China(No.52073031)the National Key Research and Development Program of China(Nos.2023YFB3208102,2021YFB3200304)+4 种基金the China National Postdoctoral Program for Innovative Talents(No.BX2021302)the Beijing Nova Program(Nos.Z191100001119047,Z211100002121148)the Fundamental Research Funds for the Central Universities(No.E0EG6801X2)the‘Hundred Talents Program’of the Chinese Academy of Sciencesthe BrainLink program funded by the MSIT through the NRF of Korea(No.RS-2023-00237308).
文摘Neuromorphic computing extends beyond sequential processing modalities and outperforms traditional von Neumann architectures in implementing more complicated tasks,e.g.,pattern processing,image recognition,and decision making.It features parallel interconnected neural networks,high fault tolerance,robustness,autonomous learning capability,and ultralow energy dissipation.The algorithms of artificial neural network(ANN)have also been widely used because of their facile self-organization and self-learning capabilities,which mimic those of the human brain.To some extent,ANN reflects several basic functions of the human brain and can be efficiently integrated into neuromorphic devices to perform neuromorphic computations.This review highlights recent advances in neuromorphic devices assisted by machine learning algorithms.First,the basic structure of simple neuron models inspired by biological neurons and the information processing in simple neural networks are particularly discussed.Second,the fabrication and research progress of neuromorphic devices are presented regarding to materials and structures.Furthermore,the fabrication of neuromorphic devices,including stand-alone neuromorphic devices,neuromorphic device arrays,and integrated neuromorphic systems,is discussed and demonstrated with reference to some respective studies.The applications of neuromorphic devices assisted by machine learning algorithms in different fields are categorized and investigated.Finally,perspectives,suggestions,and potential solutions to the current challenges of neuromorphic devices are provided.
基金the financial support given by National Natural Science Foundation of China(52227808,62202285)the National Science Foundation for Distinguished Young Scholars of China(51725505)+1 种基金the Development Fund for Shanghai Talents(No.2021003)Shanghai Collaborative Innovation Center of Intelligent Perception Chip Technology。
文摘Neuromorphic devices,inspired by the intricate architecture of the human brain,have garnered recognition for their prodigious computational speed and sophisticated parallel computing capabilities.Vision,the primary mode of external information acquisition in living organisms,has garnered substantial scholarly interest.Notwithstanding numerous studies simulating the retina through optical synapses,their applications remain circumscribed to single-mode perception.Moreover,the pivotal role of temperature,a fundamental regulator of biological activities,has regrettably been relegated to the periphery.To address these limitations,we proffer a neuromorphic device endowed with multimodal perception,grounded in the principles of light-modulated semiconductors.This device seamlessly accomplishes dynamic hybrid visual and thermal multimodal perception,featuring temperature-dependent paired pulse facilitation properties and adaptive storage.Crucially,our meticulous examination of transfer curves,capacitance–voltage(C–V)tests,and noise measurements provides insights into interface and bulk defects,elucidating the physical mechanisms underlying adaptive storage and other functionalities.Additionally,the device demonstrates a variety of synaptic functionalities,including filtering properties,Ebbinghaus curves,and memory applications in image recognition.Surprisingly,the digital recognition rate achieves a remarkable value of 98.8%.
基金supported by the National Natural Science Foundation of China(Grant Nos.62074075,62174082,and 61834001).
文摘Neuromorphic computing is a brain-inspired computing paradigm that aims to construct efficient,low-power,and adaptive computing systems by emulating the information processing mechanisms of biological neural systems.At the core of neuromorphic computing are neuromorphic devices that mimic the functions and dynamics of neurons and synapses,enabling the hardware implementation of artificial neural networks.Various types of neuromorphic devices have been proposed based on different physical mechanisms such as resistive switching devices and electric-double-layer transistors.These devices have demonstrated a range of neuromorphic functions such as multistate storage,spike-timing-dependent plasticity,dynamic filtering,etc.To achieve high performance neuromorphic computing systems,it is essential to fabricate neuromorphic devices compatible with the complementary metal oxide semiconductor(CMOS)manufacturing process.This improves the device’s reliability and stability and is favorable for achieving neuromorphic chips with higher integration density and low power consumption.This review summarizes CMOS-compatible neuromorphic devices and discusses their emulation of synaptic and neuronal functions as well as their applications in neuromorphic perception and computing.We highlight challenges and opportunities for further development of CMOS-compatible neuromorphic devices and systems.
基金Project supported by the National Natural Science Foundation of China(Grant No.51972316)Open Project of State Key Laboratory of ASIC&System(Grant No.2019KF006)+1 种基金Zhejiang Provincial Natural Science Foundation of China(Grant No.LR18F040002)Program for Ningbo Municipal Science and Technology Innovative Research Team,China(Grant No.2016B10005).
文摘Rapid developments in artificial intelligence trigger demands for perception and learning of external environments through visual perception systems.Neuromorphic devices and integrated system with photosensing and response functions can be constructed to mimic complex biological visual sensing behaviors.Here,recent progresses on optoelectronic neuromorphic memristors and optoelectronic neuromorphic transistors are briefly reviewed.A variety of visual synaptic functions stimulated on optoelectronic neuromorphic devices are discussed,including light-triggered short-term plasticities,long-term plasticities,and neural facilitation.These optoelectronic neuromorphic devices can also mimic human visual perception,information processing,and cognition.The optoelectronic neuromorphic devices that simulate biological visual perception functions will have potential application prospects in areas such as bionic neurological optoelectronic systems and intelligent robots.
基金financially supported by the National Natural Science Foundation of China(52073031,22008151)the National Key Research and Development Program of China(2021YFB3200304)+2 种基金Beijing Nova Program(Z211100002121148)Fundamental Research Funds for the Central Universities(E0EG6801X2)the‘Hundred Talents Program’of the Chinese Academy of Sciences。
文摘With the arrival of the era of artificial intelligence(AI)and big data,the explosive growth of data has raised higher demands on computer hardware and systems.Neuromorphic techniques inspired by biological nervous systems are expected to be one of the approaches to breaking the von Neumann bottleneck.Piezotronic neuromorphic devices modulate electrical transport characteristics by piezopotential and directly associate external mechanical motion with electrical output signals in an active manner,with the capability to sense/store/process information of external stimuli.In this review,we have presented the piezotronic neuromorphic devices(which are classified into strain-gated piezotronic transistors and piezoelectric nanogenerator-gated field effect transistors based on device structure)and discussed their operating mechanisms and related manufacture techniques.Secondly,we summarized the research progress of piezotronic neuromorphic devices in recent years and provided a detailed discussion on multifunctional applications,including bionic sensing,information storage,logic computing,and electrical/optical artificial synapses.Finally,in the context of future development,challenges,and perspectives,we have discussed how to modulate novel neuromorphic devices with piezotronic effects more effectively.It is believed that the piezotronic neuromorphic devices have great potential for the next generation of interactive sensation/memory/computation to facilitate the development of the Internet of Things,AI,biomedical engineering,etc.
基金supported by the National Natural Science Foundation of China(51925306,52120105006,52403255)the Strategic Priority Research Program of the Chinese Academy of Sciences(XDB0520103)+2 种基金the Information Plan of the Chinese Academy of Sciences(CAS-WX2023PY-0103)the Fundamental Research Funds for the Central UniversitiesUniversity of Chinese Academy of Sciences。
文摘Traditional von Neumann computing,with physical separation of memory and processing units,cannot satisfy the development of artificial intelligence and cloud computing.Neuromorphic computing,inspired by the human brain,has drawn much attention.All-optical neuromorphic(AON)devices employ optical signals as information carriers and leverage the neuromorphic functions to implement fast operation speed,low energy consumption,and high bandwidth of neuromorphic computing.Here,we discuss the recent progress in AON devices,including materials,device performance,working mechanisms,and applications.Moreover,the advantages and limitations of AON are presented and discussed.Finally,the perspective of AON devices points out the future research direction of neuromorphic computing.
基金the National Natural Science Foundation of China(Nos.62274035,U21A20497,61974029,and 11604051)the National Key Research and Development Program of China(Nos.2022YFB3603803 and 2022YFB3603802)+1 种基金the Natural Science Foundation of Fujian Province(Nos.2020J05104 and 2020J06012)Fujian Science&Technology Innovation Laboratory for Optoelectronic Information of China(Nos.2021ZZ129 and 2021ZZ130).
文摘Multi-sensory neuromorphic devices(MND)have broad potential in overcoming the structural bottleneck of von Neumann in the era of big data.However,the current multisensory artificial neuromorphic system is mainly based on unitary nonvolatile memory or volatile synaptic devices without intrinsic thermal sensitivity,which limits the range of biological multisensory perception and the flexibility and computational efficiency of the neural morphological computing system.Here,a temperature-dependent memory/synaptic hybrid artificial neuromorphic device based on floating gate phototransistors(FGT)is fabricated.The CsPbBr_(3)/TiO_(2)core–shell nanocrystals(NCs)prepared by in-situ pre-protection low-temperature solvothermal method were used as the photosensitive layer.The device exhibits remarkable multi-level visual memory with a large memory window of 59.6 V at room temperature.Surprisingly,when the temperature varies from 20 to 120℃back and forth,the device can switch between nonvolatile memory and volatile synaptic device with reconfigurable and reversible behaviors,which contributes to the efficient visual/thermal fusion perception.This work expands the sensory range of multisensory devices and promotes the development of memory and neuromorphic devices based on organic field-effect transistors(OFET).
基金supported by the National Science Foundation for Distinguished Young Scholars of China(Grant No.12425209)the National Natural Science Foundation of China(Grant No.U20A20390,11827803,12172034,11822201,62004056,62104058,62271269).
文摘Neuromorphic devices have shown great potential in simulating the function of biological neurons due to their efficient parallel information processing and low energy consumption.MXene-Ti_(3)C_(2)T_(x),an emerging twodimensional material,stands out as an ideal candidate for fabricating neuromorphic devices.Its exceptional electrical performance and robust mechanical properties make it an ideal choice for this purpose.This review aims to uncover the advantages and properties of MXene-Ti_(3)C_(2)T_(x)in neuromorphic devices and to promote its further development.Firstly,we categorize several core physical mechanisms present in MXene-Ti_(3)C_(2)T_(x)neuromorphic devices and summarize in detail the reasons for their formation.Then,this work systematically summarizes and classifies advanced techniques for the three main optimization pathways of MXene-Ti_(3)C_(2)T_(x),such as doping engineering,interface engineering,and structural engineering.Significantly,this work highlights innovative applications of MXene-Ti_(3)C_(2)T_(x)neuromorphic devices in cutting-edge computing paradigms,particularly near-sensor computing and in-sensor computing.Finally,this review carefully compiles a table that integrates almost all research results involving MXene-Ti_(3)C_(2)T_(x)neuromorphic devices and discusses the challenges,development prospects,and feasibility of MXene-Ti_(3)C_(2)T_(x)-based neuromorphic devices in practical applications,aiming to lay a solid theoretical foundation and provide technical support for further exploration and application of MXene-Ti_(3)C_(2)T_(x)in the field of neuromorphic devices.
基金supported by the National Research Foundation(NRF)Grant funded by the Korean government(MSIT)(Nos.RS-2023-00208538,RS-2024-00411904,and RS-2023-00237308).
文摘Two-dimensional (2D) materials have attracted significant attention as resistive switching materials for two-terminal non-volatile memory devices, often referred to as memristors, due to their potential for achieving fast switching speeds and low power consumption. Their excellent gate tunability in electronic properties also enables hybrid devices combining the functionality of memory devices and transistors, with the possibility of realizing large-scale memristive crossbar arrays with high integration density. To facilitate the use of 2D materials in practical memristor applications, scalable synthesis of 2D materials with high electronic quality is critical. In addition, low-temperature integration for complementary metal oxide semiconductor (CMOS) back-end-of-line (BEOL) integration is important for embedded memory applications. Solution-based exfoliation has been actively explored as a facile, cost-effective method for the mass production and low-temperature integration of 2D materials. However, the films produced from the resulting 2D nanosheet dispersions exhibited poor electrical properties in the early stages of research, thereby hindering their use in electronic devices. Recent progress in the exfoliation process and post-processing has led to significant improvements in the electronic performance of solution-processed 2D materials, driving increased adoption of these materials in memristor research. In this review article, we provide a thorough overview of the progress and current status of memristive devices utilizing solution-processed 2D resistive switching layers. We begin by introducing the electrical characteristics and resistive switching mechanisms of memristors fabricated with conventional materials to lay the groundwork for understanding memristive behavior in 2D materials. Representative solution-based exfoliation and film formation techniques are also introduced, emphasizing the benefits of these approaches for obtaining scalable 2D material films compared to conventional methods such as mechanical exfoliation and chemical vapor deposition. Finally, we explore the electrical characteristics, resistive switching mechanisms, and applications of solution-processed 2D memristive devices, discussing their advantages and remaining challenges.
文摘Robots are widely used,providing significant convenience in daily life and production.With the rapid development of artificial intelligence and neuromorphic computing in recent years,the realization of more intelligent robots through a pro-found intersection of neuroscience and robotics has received much attention.Neuromorphic circuits based on memristors used to construct hardware neural networks have proved to be a promising solution of shattering traditional control limita-tions in the field of robot control,showcasing characteristics that enhance robot intelligence,speed,and energy efficiency.Start-ing with introducing the working mechanism of memristors and peripheral circuit design,this review gives a comprehensive analysis on the biomimetic information processing and biomimetic driving operations achieved through the utilization of neuro-morphic circuits in brain-like control.Four hardware neural network approaches,including digital-analog hybrid circuit design,novel device structure design,multi-regulation mechanism,and crossbar array,are summarized,which can well simulate the motor decision-making mechanism,multi-information integration and parallel control of brain at the hardware level.It will be definitely conductive to promote the application of memristor-based neuromorphic circuits in areas such as intelligent robotics,artificial intelligence,and neural computing.Finally,a conclusion and future prospects are discussed.
基金supported by the National Research Foundation of Korea(No.2021R1A2C2095322)supported by Grant Nos.RS-2023-00260527,RS-2023-00231985,RS2023-00235655,and RS-2024-00406007supported by BK21 FOUR(Connected AI Education&Research Program for Industry and Society Innovation,KAIST EE,No.4120200113769).
文摘Next-generation artificial tactile systems demand seamless integration with neuromorphic architectures to support on-edge computation and high-fidelity sensory signal processing.Despite significant advancements,current research remains predominantly focused on optimizing individual sensor elements,and systems utilizing single neuromorphic components encounter inherent limitations in enhancing overall functionality.Here,we present a vertically integrated in-sensor processing platform,which combines a three-dimensional antiferroelectric field-effect transistor(AFEFET)device with an aluminum nitride(AlN)piezoelectric sensor.
基金financial support by the self-supporting project of Pazhou Lab(No.PZL2023ZZ0011)by National Key R&D Program of China(No.2019YFA0904801).
文摘Rapid development of artificial intelligence requires the implementation of hardware systems with bioinspired parallel information processing and presentation and energy efficiency.Electrolyte-gated organic transistors(EGOTs)offer significant advantages as neuromorphic devices due to their ultra-low operation voltages,minimal hardwired connectivity,and similar operation environment as electrophysiology.Meanwhile,ionic–electronic coupling and the relatively low elastic moduli of organic channel materials make EGOTs suitable for interfacing with biology.This review presents an overview of the device architectures based on organic electrochemical transistors and organic field-effect transistors.Furthermore,we review the requirements of low energy consumption and tunable synaptic plasticity of EGOTs in emulating biological synapses and how they are affected by the organic materials,electrolyte,architecture,and operation mechanism.In addition,we summarize the basic operation principle of biological sensory systems and the recent progress of EGOTs as a building block in artificial systems.Finally,the current challenges and future development of the organic neuromorphic devices are discussed.
基金the Hong Kong Research Grants Council,Young Collaborative Research Grant(No.C5001-24)Research Institute for Smart Energy(No.UCDC9)+10 种基金Guangdong Provincial Department of Science and Technology(No.2024B1515040002)RSC Sustainable Laboratories Grant(No.L24-8215098370)Guangdong Basic and Applied Basic Research Foundation(No.2023A1515012479)the Science and Technology Innovation Commission of Shenzhen(No.JCYJ20220818100206013)RSC Researcher Collaborations Grant(No.C23-2422436283)State Key Laboratory of Radio Frequency Heterogeneous Integration(Independent Scientific Research Program No.2024010)NTUT-SZU Joint Research Programsupported by the National Natural Science Foundation of China(No.52373248)Guangdong Provincial Department of Science and Technology(Nos.2024A1515010006 and 2024A1515011718)Guangdong Basic and Applied Basic Research Foundation(Nos.2023A1515012479 and 2025A1515011274)the Science and Technology Innovation Commission of Shenzhen(Nos.JCYJ20230808105900001,JCYJ20220531102214032,20231123155543001,and JCYJ20240813141813018).
文摘Multisensory integration allows biological organisms to merge information from various sensory modalities,enhancing perception,decision-making,and adaptability in complex environments.This process,involving specialized cortical and subcortical areas,reduces uncertainty,speeds up responses,enriches perception,and supports adaptive behaviors.Recent findings reveal that even primary sensory cortices contribute to multisensory processing,further boosting adaptability and decisionmaking.Inspired by these natural capabilities,researchers aim to develop artificial systems replicating biological sensory integration to address challenges in robotics,artificial intelligence,and big data.Current artificial systems,often reliant on single-modal perception,struggle in dynamic environments due to their limited adaptability.Advances in materials,device architectures,and neuromorphic technologies,such as memristor-and transistor-based neurons,are enabling the development of multimodal systems with enhanced efficiency,flexibility,and functionality.This review explores strategies to overcome single-modal limitations,focusing on synchronization,fusion,and deep interpretation of sensory data.Future directions emphasize improving integration density,novel device designs,and adaptable mechanisms.Multimodal systems hold promise to revolutionize artificial perception,narrowing the gap between biological systems and intelligent technologies.
基金financially supported by the National Natural Science Foundation of China(No.12404135)the Science and Technology Foundation for Youths of Gansu Province(No.24JRRA466)+1 种基金the Open Research Fund of Songshan Lake Materials Laboratory(No.2023SLABFN05)Talent Scientific Fund of Lanzhou University
文摘Current-driven spintronic artificial neural networks(ANNs) hold great promise for image recognition but are limited by excessive power consumption.Surface acoustic waves(SAWs) have recently emerged as a disruptive alternative,offering ultralow-power control over magnetization through the magnetoelastic and acoustothermal effects.In this work,for the first time,we demonstrate a SAW-driven neuromorphic computing paradigm utilizing FeRh magnetic phase transitions,achieving both ReLU neuron activation and robust synaptic plasticity.Notably,the power density of our neuromorphic devices is reduced by an order of magnitude compared to that of conventional spintronic-based devices,enabling power-efficient image recognition with an accuracy exceeding 91%.We also demonstrate that ANNs implemented with our neuromorphic devices can precisely and autonomously assess left ventricular ejection fraction,a key clinical metric for evaluating cardiac function.Our findings establish SAWs as a transformative enabler for next-generation neuromorphic computing,paving the way for energy-efficient,high-precision artificial intelligence in both advanced image processing and medical diagnostics.
基金the National Key Research and Development Program of China (2022YFB3803300)the open research fund of Songshan Lake Materials Laboratory (2021SLABFK02)the National Natural Science Foundation of China (21961160720)。
文摘Nowadays, the soar of photovoltaic performance of perovskite solar cells has set off a fever in the study of metal halide perovskite materials. The excellent optoelectronic properties and defect tolerance feature allow metal halide perovskite to be employed in a wide variety of applications. This article provides a holistic review over the current progress and future prospects of metal halide perovskite materials in representative promising applications, including traditional optoelectronic devices(solar cells, light-emitting diodes, photodetectors, lasers), and cutting-edge technologies in terms of neuromorphic devices(artificial synapses and memristors) and pressure-induced emission. This review highlights the fundamentals, the current progress and the remaining challenges for each application, aiming to provide a comprehensive overview of the development status and a navigation of future research for metal halide perovskite materials and devices.
基金supported by the National Key Research and Development Program from Ministry of Science and Technology(No.2023YFB3208102)the National Natural Science Foundation of China(No.52073031)the“Hundred Talents Program”of the Chinese Academy of Sciences.
文摘The advent of the Internet of Things(IoT)era has significantly accelerated advancements in neuromorphic computing research.Triboelectric nanogenerators(TENGs)exhibit dual functionality as both energy harvesters and synaptic simulators,facilitated by their inherent mechanoelectrical transduction properties and seamless circuit integration capabilities.In this work,we presented a vertically contact-separated paper-based artificial synaptic device employing TENG technology.The fabricated device successfully replicates fundamental synaptic behaviors,including paired-pulse facilitation(PPF),high-pass filtering characteristics,and spatiotemporal dynamic logic operations.Through optimized circuit configurations,we achieved elementary“NOT”logic gate using single devices,while implementing“AND/NAND”logic gates and“OR/NOR”logic gates operations through two-and three-device assemblies,respectively.Capitalizing on the mechanical flexibility and lightweight of paper substrates,we further developed a trilayer artificial synaptic architecture that mimics hierarchical neural information processing.This mechanoelectrical coupling approach establishes a novel paradigm for flexible neuromorphic systems,demonstrating exceptional potential for environmentally interactive robotics and adaptive wearable prosthetics.
基金supported by the National Natural Science Foundation of China(No.12304023)the Taishan Scholars Project Special Funds(Nos.tsqn202312035 and tsqn202306068)+3 种基金the Shandong Provincial Natural Science Foundation for Excellent Young Scientists Fund Program(Overseas)(No.2023HWYQ-037)the Shandong Provincial Natural Science Foundation(No.ZR2023QF066)the Guangdong Basic and Applied Basic Research Foundation(No.2022A1515110464)Qilu Young Scholar Program of Shandong University.
文摘Drawing inspiration from the human visual system’s exceptional capabilities in information processing and memory retention,optoelectronic neuromorphic devices have been considered a cutting-edge solution to mimic these key functions.These devices,particularly optoelectronic memristors,promise to revolutionize neuromorphic computing and visual biomimetic functions,holding significant potential to surpass the traditional von Neumann architecture.Herein,an optoelectronic memristor engineered from a MoS_(2)/WO_(3)heterojunction is developed and integrated with optoelectronic synapses and optical perception capabilities.The device exhibits short/long-term synaptic plasticity under electrical and optical stimuli,effectively mimicking short/long-term memory and“learning-forgetting-relearning”.Leveraging its optical synaptic characteristics,the device successfully simulates complex synaptic behaviors,including Pavlovian conditioning,enabling visual associative learning similar to the biological brain.Through coordinated optoelectronic modulation of long-term potentiation/depression for synaptic weight,the system achieves 98.4%classification accuracy on the Modified National Institute of Standards and Technology(MNIST)handwritten digit recognition task.Moreover,a 4×4 optoelectronic memristor array demonstrates stable visual perception and memory functions under four distinct optical stimuli,facilitating adjustable image memory properties across different light wavelengths.This research advances the application of optoelectronic memristors in neuromorphic computing and bionic visual systems.
基金supported by the National Science Foundation for Distinguished Young Scholars of China(Grant No.12425209)the National Natural Science Foundation of China(11827803,12172034,62004056,62104058,62271269).
文摘The modern medical field faces two critical challenges:the dramatic increase in data complexity and the explosive growth in data size.Especially in current research,medical diagnostic,and data processing devices relying on traditional computer architecture are increasingly showing limitations when faced with dynamic temporal and spatial processing requirements,as well as high-dimensional data processing tasks.Neuromorphic devices provide a new way for biomedical data processing due to their low energy consumption and high dynamic information processing capabilities.This paper aims to reveal the advantages of neuromorphic devices in biomedical applications.First,this review emphasizes the urgent need of biomedical engineering for diversify clinical diagnostic techniques.Secondly,the feasibility of the application in biomedical engineering is demonstrated by reviewing the historical development of neuromorphic devices from basic modeling to multimodal signal processing.In addition,this paper demonstrates the great potential of neuromorphic chips for application in the fields of biosensing technology,medical image processing and generation,rehabilitation medical engineering,and brain-computer interfaces.Finally,this review provides the pathways for constructing standardized experimental protocols using biocompatible technologies,personalized treatment strategies,and systematic clinical validation.In summary,neuromorphic devices will drive technological innovation in the biomedical field and make significant contributions to life health.
基金supported by the National Natural Science Foundation of China(22175184 and 22105207)the CAS Project for Young Scientists in Basic Research(YSBR-053)+1 种基金the Strategic Priority Research Programme of the Chinese Academy of Sciences(XDB0520202)the CAS Project for Young Scientists in Interdisciplinary Research.
文摘Scaling of complementary metal-oxide-semiconductor technology nodes using conventional semiconducting materials is slowing down.The development of semiconductor technology with new materials and new concepts has become an important focus of scientific and industrial research.In recent years,emerging ambipolar two-dimensional(2D)materials-based reconfigurable devices have shown their potential in high-integration,multifunctional circuits and have begun to attract the attention of researchers.Here,we summarize the latest progress in the field concerning ambipolar 2D materials-based reconfigurable devices.Firstly,we introduce the basic properties and preparation methods of ambipolar 2D materials.Secondly,we discuss the latest applications of reconfigurable devices based on ambipolar 2D materials.Furthermore,we also introduce the current research status of ambipolar material devices in large-scale integration.Finally,we analyze the challenges faced during the development of ambipolar 2D materials-based reconfigurable devices and provide prospects for their future development.
基金supported by National Natural Science Foundation of China(Grant no.62074075).
文摘Emulating brain functionality with neuromorphic devices is an emerging field of research.It is extensively considered as the first step to overcome the limitations of conventional von Neumann systems and build artificial intelligent systems.Cur-rently,most neuromorphic transistors are manufactured on rigid substrates,which are difficult to bend and cannot closely fit soft human skin,limiting their appliction scope.The emergence and evolution of flexible electronic devices address a plethora of application and scenario demands.Particularly,the introduction of flexible neuromorphic transistors injects fresh vitality into neuromorphic computing and perception,symbolizing a significant step towards overcoming the limitations of conventional computational models and fostering the development of more intelligent wearable devices.Herein,the recent developments in felxible neuromorphic transistors are summarized and their applications in neuromorphic computing and artificial perception systems are highlighted.The future prospects and challenges of felxible neuromorphic transistors are also discussed.We believe developments in felxible neuromorphic transistors will shed light on future advances in wearable artificial intelligent systems,humanoid robotics and neural repair technology.
