Neuromorphic computing has the potential to overcome limitations of traditional silicon technology in machine learning tasks.Recent advancements in large crossbar arrays and silicon-based asynchronous spiking neural n...Neuromorphic computing has the potential to overcome limitations of traditional silicon technology in machine learning tasks.Recent advancements in large crossbar arrays and silicon-based asynchronous spiking neural networks have led to promising neuromorphic systems.However,developing compact parallel computing technology for integrating artificial neural networks into traditional hardware remains a challenge.Organic computational materials offer affordable,biocompatible neuromorphic devices with exceptional adjustability and energy-efficient switching.Here,the review investigates the advancements made in the development of organic neuromorphic devices.This review explores resistive switching mechanisms such as interface-regulated filament growth,molecular-electronic dynamics,nanowire-confined filament growth,and vacancy-assisted ion migration,while proposing methodologies to enhance state retention and conductance adjustment.The survey examines the challenges faced in implementing low-power neuromorphic computing,e.g.,reducing device size and improving switching time.The review analyses the potential of these materials in adjustable,flexible,and low-power consumption applications,viz.biohybrid spiking circuits interacting with biological systems,systems that respond to specific events,robotics,intelligent agents,neuromorphic computing,neuromorphic bioelectronics,neuroscience,and other applications,and prospects of this technology.展开更多
In recent years,research focusing on synaptic device based on phototransistors has provided a new method for asso-ciative learning and neuromorphic computing.A TiO_(2)/AlGaN/GaN heterostructure-based synaptic phototra...In recent years,research focusing on synaptic device based on phototransistors has provided a new method for asso-ciative learning and neuromorphic computing.A TiO_(2)/AlGaN/GaN heterostructure-based synaptic phototransistor is fabricated and measured,integrating a TiO_(2)nanolayer gate and a two-dimensional electron gas(2DEG)channel to mimic the synaptic weight and the synaptic cleft,respectively.The maximum drain to source current is 10 nA,while the device is driven at a reverse bias not exceeding-2.5 V.A excitatory postsynaptic current(EPSC)of 200 nA can be triggered by a 365 nm UVA light spike with the duration of 1 s at light intensity of 1.35μW·cm^(-2).Multiple synaptic neuromorphic functions,including EPSC,short-term/long-term plasticity(STP/LTP)and paried-pulse facilitation(PPF),are effectively mimicked by our GaN-based het-erostructure synaptic device.In the typical Pavlov’s dog experiment,we demonstrate that the device can achieve"retraining"process to extend memory time through enhancing the intensity of synaptic weight,which is similar to the working mecha-nism of human brain.展开更多
The traditional von Neumann architecture faces inherent limitations due to the separation of memory and computa-tion,leading to high energy consumption,significant latency,and reduced operational efficiency.Neuromorph...The traditional von Neumann architecture faces inherent limitations due to the separation of memory and computa-tion,leading to high energy consumption,significant latency,and reduced operational efficiency.Neuromorphic computing,inspired by the architecture of the human brain,offers a promising alternative by integrating memory and computational func-tions,enabling parallel,high-speed,and energy-efficient information processing.Among various neuromorphic technologies,ion-modulated optoelectronic devices have garnered attention due to their excellent ionic tunability and the availability of multi-dimensional control strategies.This review provides a comprehensive overview of recent progress in ion-modulation optoelec-tronic neuromorphic devices.It elucidates the key mechanisms underlying ionic modulation of light fields,including ion migra-tion dynamics and capture and release of charge through ions.Furthermore,the synthesis of active materials and the proper-ties of these devices are analyzed in detail.The review also highlights the application of ion-modulation optoelectronic devices in artificial vision systems,neuromorphic computing,and other bionic fields.Finally,the existing challenges and future direc-tions for the development of optoelectronic neuromorphic devices are discussed,providing critical insights for advancing this promising field.展开更多
To address the increasing demand for massive data storage and processing,brain-inspired neuromorphic comput-ing systems based on artificial synaptic devices have been actively developed in recent years.Among the vario...To address the increasing demand for massive data storage and processing,brain-inspired neuromorphic comput-ing systems based on artificial synaptic devices have been actively developed in recent years.Among the various materials inves-tigated for the fabrication of synaptic devices,silicon carbide(SiC)has emerged as a preferred choices due to its high electron mobility,superior thermal conductivity,and excellent thermal stability,which exhibits promising potential for neuromorphic applications in harsh environments.In this review,the recent progress in SiC-based synaptic devices is summarized.Firstly,an in-depth discussion is conducted regarding the categories,working mechanisms,and structural designs of these devices.Subse-quently,several application scenarios for SiC-based synaptic devices are presented.Finally,a few perspectives and directions for their future development are outlined.展开更多
The traditional von Neumann architecture has demonstrated inefficiencies in parallel computing and adaptive learn-ing,rendering it incapable of meeting the growing demand for efficient and high-speed computing.Neuromo...The traditional von Neumann architecture has demonstrated inefficiencies in parallel computing and adaptive learn-ing,rendering it incapable of meeting the growing demand for efficient and high-speed computing.Neuromorphic comput-ing with significant advantages such as high parallelism and ultra-low power consumption is regarded as a promising pathway to overcome the limitations of conventional computers and achieve the next-generation artificial intelligence.Among various neuromorphic devices,the artificial synapses based on electrolyte-gated transistors stand out due to their low energy consump-tion,multimodal sensing/recording capabilities,and multifunctional integration.Moreover,the emerging optoelectronic neuro-morphic devices which combine the strengths of photonics and electronics have demonstrated substantial potential in the neu-romorphic computing field.Therefore,this article reviews recent advancements in electrolyte-gated optoelectronic neuromor-phic transistors.First,it provides an overview of artificial optoelectronic synapses and neurons,discussing aspects such as device structures,operating mechanisms,and neuromorphic functionalities.Next,the potential applications of optoelectronic synapses in different areas such as artificial visual system,pain system,and tactile perception systems are elaborated.Finally,the current challenges are summarized,and future directions for their developments are proposed.展开更多
As an emerging memory device,memristor shows great potential in neuromorphic computing applications due to its advantage of low power consumption.This review paper focuses on the application of low-power-based memrist...As an emerging memory device,memristor shows great potential in neuromorphic computing applications due to its advantage of low power consumption.This review paper focuses on the application of low-power-based memristors in various aspects.The concept and structure of memristor devices are introduced.The selection of functional materials for low-power memristors is discussed,including ion transport materials,phase change materials,magnetoresistive materials,and ferroelectric materials.Two common types of memristor arrays,1T1R and 1S1R crossbar arrays are introduced,and physical diagrams of edge computing memristor chips are discussed in detail.Potential applications of low-power memristors in advanced multi-value storage,digital logic gates,and analogue neuromorphic computing are summarized.Furthermore,the future challenges and outlook of neuromorphic computing based on memristor are deeply discussed.展开更多
As traditional von Neumann architectures face limitations in handling the demands of big data and complex computa-tional tasks,neuromorphic computing has emerged as a promising alternative,inspired by the human brain&...As traditional von Neumann architectures face limitations in handling the demands of big data and complex computa-tional tasks,neuromorphic computing has emerged as a promising alternative,inspired by the human brain's neural networks.Volatile memristors,particularly Mott and diffusive memristors,have garnered significant attention for their ability to emulate neuronal dynamics,such as spiking and firing patterns,enabling the development of reconfigurable and adaptive computing systems.Recent advancements include the implementation of leaky integrate-and-fire neurons,Hodgkin-Huxley neurons,opto-electronic neurons,and time-surface neurons,all utilizing volatile memristors to achieve efficient,low-power,and highly inte-grated neuromorphic systems.This paper reviews the latest progress in volatile memristor-based artificial neurons,highlight-ing their potential for energy-efficient computing and integration with artificial synapses.We conclude by addressing chal-lenges such as improving memristor reliability and exploring new architectures to advance memristor-based neuromorphic com-puting.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
With the rise of artificial intelligence(AI),neuromorphic sensory systems that emulate the five basic human sensations including tactility,audition,olfaction,gustation,and vision have attracted significant attention.I...With the rise of artificial intelligence(AI),neuromorphic sensory systems that emulate the five basic human sensations including tactility,audition,olfaction,gustation,and vision have attracted significant attention.In particular,research on integrating sensors with artificial synapses is being carried out extensively.These studies offer valuable opportunities for making another breakthrough in AI technology,including autonomous systems,real-time monitoring systems,and human-machine interactions.In this review,we introduce promising reports of neuromorphic sensory systems.Specifically,the core sensing material,device architecture,fabrication process,and applications of the proposed systems are presented in detail.Finally,the unsolved challenges and the prospects of neuromorphic sensory systems are discussed.展开更多
Artificial multisensory devices play a key role in human-computer interaction in the field of artificial intelligence(AI).In this work,we have designed and constructed a novel olfactory-visual bimodal neuromorphic car...Artificial multisensory devices play a key role in human-computer interaction in the field of artificial intelligence(AI).In this work,we have designed and constructed a novel olfactory-visual bimodal neuromorphic carbon nanotube thin film transistor(TFT)arrays for artificial olfactory-visual multisensory synergy recognition with a very low power consumption of 25 aJ for a single pulse,employing semiconducting single-walled carbon nanotubes(sc-SWCNTs)as channel materials and gas sensitive materials,and poly[[4,8-bis[5-(2-ethylhexyl)-2-thienyl]benzo[1,2-b:4,5-b0]dithiophene-2,6-diyl]-2,5-thiophenediyl-[5,7-bis(2-ethylhexyl)-4,8-dioxo-4H,8H-benzo[1,2-c:4,5-c0]dithio-phene-1,3-diyl]](PBDB-T)as the photosensitive material.It is noted that it is the first time to realize the simulation of olfactory and visual senses(from 280 nm to 650 nm)with the wide operating temperature range(0-150℃)in a single SWCNT TFT device and successfully simulate the recovery of olfactory senses after COVID-19 by olfactory-visual synergy.Furthermore,our SWCNT neuromorphic TFT devices with a high IOn/IOff ratio(up to 10^(6))at a low operating voltage(−2 to 0.5 V)can mimic not only the basic biological synaptic functions of olfaction and vision(such as paired-pulse facilitation,short-term plasticity,and long-term plasticity),but also optical wireless communication by Morse code.The proposed multisensory,broadband light-responsive,low-power synaptic devices provide great potential for developing AI robots to face complex external environments.展开更多
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
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
Artificial skin should embody a softly functional film that is capable of self-powering,healing and sensing with neuromorphic processing.However,the pursuit of a bionic skin that combines high flexibility,self-healabi...Artificial skin should embody a softly functional film that is capable of self-powering,healing and sensing with neuromorphic processing.However,the pursuit of a bionic skin that combines high flexibility,self-healability,and zero-powered photosynaptic functionality remains elusive.In this study,we report a self-powered and self-healable neuromorphic vision skin,featuring silver nanoparticle-doped ionogel heterostructure as photoacceptor.The localized surface plasmon resonance induced by light in the nanoparticles triggers temperature fluctuations within the heterojunction,facilitating ion migration for visual sensing with synaptic behaviors.The abundant reversible hydrogen bonds in the ionogel endow the skin with remarkable mechanical flexibility and self-healing properties.We assembled a neuromorphic visual skin equipped with a 5×5 photosynapse array,capable of sensing and memorizing diverse light patterns.展开更多
Organic electrochemical transistors have emerged as a solution for artificial synapses that mimic the neural functions of the brain structure,holding great potentials to break the bottleneck of von Neumann architectur...Organic electrochemical transistors have emerged as a solution for artificial synapses that mimic the neural functions of the brain structure,holding great potentials to break the bottleneck of von Neumann architectures.However,current artificial synapses rely primarily on electrical signals,and little attention has been paid to the vital role of neurotransmitter-mediated artificial synapses.Dopamine is a key neurotransmitter associated with emotion regulation and cognitive processes that needs to be monitored in real time to advance the development of disease diagnostics and neuroscience.To provide insights into the development of artificial synapses with neurotransmitter involvement,this review proposes three steps towards future biomimic and bioinspired neuromorphic systems.We first summarize OECT-based dopamine detection devices,and then review advances in neurotransmitter-mediated artificial synapses and resultant advanced neuromorphic systems.Finally,by exploring the challenges and opportunities related to such neuromorphic systems,we provide a perspective on the future development of biomimetic and bioinspired neuromorphic systems.展开更多
To emulate the functionality of the human retina and achieve a neuromorphic visual system,the development of a photonic synapse capable of multispectral color discrimination is of paramount importance.However,attainin...To emulate the functionality of the human retina and achieve a neuromorphic visual system,the development of a photonic synapse capable of multispectral color discrimination is of paramount importance.However,attaining robust color discrimination across a wide intensity range,even irrespective of medium limitations in the channel layer,poses a significant challenge.Here,we propose an approach that can bestow the color-discriminating synaptic functionality upon a three-terminal transistor flash memory even with enhanced discriminating capabilities.By incorporating the strong induced dipole moment effect at the excitation,modulated by the wavelength of the incident light,into the floating gate,we achieve outstanding RGB color-discriminating synaptic functionality within a remarkable intensity range spanning from 0.05 to 40 mW cm^(-2).This approach is not restricted to a specific medium in the channel layer,thereby enhancing its applicability.The effectiveness of this color-discriminating synaptic functionality is demonstrated through visual pre-processing of a photonic synapse array,involving the differentiation of RGB channels and the enhancement of image contrast with noise reduction.Consequently,a convolutional neural network can achieve an impressive inference accuracy of over 94%for Canadian-Institute-For-Advanced-Research-10 colorful image recognition task after the pre-processing.Our proposed approach offers a promising solution for achieving robust and versatile RGB color discrimination in photonic synapses,enabling significant advancements in artificial visual systems.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
The rapid advancement of deep learning and the emergence of largescale neural models,such as bidirectional encoder representations from transformers(BERT),generative pre-trained transformer(GPT),and large language mod...The rapid advancement of deep learning and the emergence of largescale neural models,such as bidirectional encoder representations from transformers(BERT),generative pre-trained transformer(GPT),and large language model Meta AI(LLaMa),have brought significant computational and energy challenges.Neuromorphic computing presents a biologically inspired approach to addressing these issues,leveraging event-driven processing and in-memory computation for enhanced energy efficiency.This survey explores the intersection of neuromorphic computing and large-scale deep learning models,focusing on neuromorphic models,learning methods,and hardware.We highlight transferable techniques from deep learning to neuromorphic computing and examine the memoryrelated scalability limitations of current neuromorphic systems.Furthermore,we identify potential directions to enable neuromorphic systems to meet the growing demands of modern AI workloads.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
In the past decade,there has been tremendous progress in integrating chalcogenide phase-change materials(PCMs)on the silicon photonic platform for non-volatile memory to neuromorphic in-memory computing applications.I...In the past decade,there has been tremendous progress in integrating chalcogenide phase-change materials(PCMs)on the silicon photonic platform for non-volatile memory to neuromorphic in-memory computing applications.In particular,these non von Neumann computational elements and systems benefit from mass manufacturing of silicon photonic integrated circuits(PICs)on 8-inch wafers using a 130 nm complementary metal-oxide semiconductor line.Chip manufacturing based on deep-ultraviolet lithography and electron-beam lithography enables rapid prototyping of PICs,which can be integrated with high-quality PCMs based on the wafer-scale sputtering technique as a back-end-of-line process.In this article,we present an overview of recent advances in waveguide integrated PCM memory cells,functional devices,and neuromorphic systems,with an emphasis on fabrication and integration processes to attain state-of-the-art device performance.After a short overview of PCM based photonic devices,we discuss the materials properties of the functional layer as well as the progress on the light guiding layer,namely,the silicon and germanium waveguide platforms.Next,we discuss the cleanroom fabrication flow of waveguide devices integrated with thin films and nanowires,silicon waveguides and plasmonic microheaters for the electrothermal switching of PCMs and mixed-mode operation.Finally,the fabrication of photonic and photonic–electronic neuromorphic computing systems is reviewed.These systems consist of arrays of PCM memory elements for associative learning,matrix-vector multiplication,and pattern recognition.With large-scale integration,the neuromorphic photonic computing paradigm holds the promise to outperform digital electronic accelerators by taking the advantages of ultra-high bandwidth,high speed,and energy-efficient operation in running machine learning algorithms.展开更多
Neuromorphic computing systems,which mimic the operation of neurons and synapses in the human brain,are seen as an appealing next-generation computing method due to their strong and efficient computing abilities.Two-d...Neuromorphic computing systems,which mimic the operation of neurons and synapses in the human brain,are seen as an appealing next-generation computing method due to their strong and efficient computing abilities.Two-dimensional (2D) materials with dangling bond-free surfaces and atomic-level thicknesses have emerged as promising candidates for neuromorphic computing hardware.As a result,2D neuromorphic devices may provide an ideal platform for developing multifunctional neuromorphic applications.Here,we review the recent neuromorphic devices based on 2D material and their multifunctional applications.The synthesis and next micro–nano fabrication methods of 2D materials and their heterostructures are first introduced.The recent advances of neuromorphic 2D devices are discussed in detail using different operating principles.More importantly,we present a review of emerging multifunctional neuromorphic applications,including neuromorphic visual,auditory,tactile,and nociceptive systems based on 2D devices.In the end,we discuss the problems and methods for 2D neuromorphic device developments in the future.This paper will give insights into designing 2D neuromorphic devices and applying them to the future neuromorphic systems.展开更多
基金financially supported by the Ministry of Education(Singapore)(MOE-T2EP50220-0022)SUTD-MIT International Design Center(Singapore)+3 种基金SUTD-ZJU IDEA Grant Program(SUTD-ZJU(VP)201903)SUTD Kickstarter Initiative(SKI 2021_02_03,SKI 2021_02_17,SKI 2021_01_04)Agency of Science,Technology and Research(Singapore)(A20G9b0135)National Supercomputing Centre(Singapore)(15001618)。
文摘Neuromorphic computing has the potential to overcome limitations of traditional silicon technology in machine learning tasks.Recent advancements in large crossbar arrays and silicon-based asynchronous spiking neural networks have led to promising neuromorphic systems.However,developing compact parallel computing technology for integrating artificial neural networks into traditional hardware remains a challenge.Organic computational materials offer affordable,biocompatible neuromorphic devices with exceptional adjustability and energy-efficient switching.Here,the review investigates the advancements made in the development of organic neuromorphic devices.This review explores resistive switching mechanisms such as interface-regulated filament growth,molecular-electronic dynamics,nanowire-confined filament growth,and vacancy-assisted ion migration,while proposing methodologies to enhance state retention and conductance adjustment.The survey examines the challenges faced in implementing low-power neuromorphic computing,e.g.,reducing device size and improving switching time.The review analyses the potential of these materials in adjustable,flexible,and low-power consumption applications,viz.biohybrid spiking circuits interacting with biological systems,systems that respond to specific events,robotics,intelligent agents,neuromorphic computing,neuromorphic bioelectronics,neuroscience,and other applications,and prospects of this technology.
基金supported by the National Key R&D Program of China(2021YFB3601000,2021YFB3601004)the National Key R&D Program of China(2022YFB3604702)the Chinese Academy of Sciences.
文摘In recent years,research focusing on synaptic device based on phototransistors has provided a new method for asso-ciative learning and neuromorphic computing.A TiO_(2)/AlGaN/GaN heterostructure-based synaptic phototransistor is fabricated and measured,integrating a TiO_(2)nanolayer gate and a two-dimensional electron gas(2DEG)channel to mimic the synaptic weight and the synaptic cleft,respectively.The maximum drain to source current is 10 nA,while the device is driven at a reverse bias not exceeding-2.5 V.A excitatory postsynaptic current(EPSC)of 200 nA can be triggered by a 365 nm UVA light spike with the duration of 1 s at light intensity of 1.35μW·cm^(-2).Multiple synaptic neuromorphic functions,including EPSC,short-term/long-term plasticity(STP/LTP)and paried-pulse facilitation(PPF),are effectively mimicked by our GaN-based het-erostructure synaptic device.In the typical Pavlov’s dog experiment,we demonstrate that the device can achieve"retraining"process to extend memory time through enhancing the intensity of synaptic weight,which is similar to the working mecha-nism of human brain.
基金supported by National Natural Science Foundation of China(62174164,U23A20568,and U22A2075)National Key Research and Development Project(2021YFA1202600)+2 种基金Talent Plan of Shanghai Branch,Chinese Academy of Sciences(CASSHB-QNPD-2023-022)Ningbo Technology Project(2022A-007-C)Ningbo Key Research and Development Project(2023Z021).
文摘The traditional von Neumann architecture faces inherent limitations due to the separation of memory and computa-tion,leading to high energy consumption,significant latency,and reduced operational efficiency.Neuromorphic computing,inspired by the architecture of the human brain,offers a promising alternative by integrating memory and computational func-tions,enabling parallel,high-speed,and energy-efficient information processing.Among various neuromorphic technologies,ion-modulated optoelectronic devices have garnered attention due to their excellent ionic tunability and the availability of multi-dimensional control strategies.This review provides a comprehensive overview of recent progress in ion-modulation optoelec-tronic neuromorphic devices.It elucidates the key mechanisms underlying ionic modulation of light fields,including ion migra-tion dynamics and capture and release of charge through ions.Furthermore,the synthesis of active materials and the proper-ties of these devices are analyzed in detail.The review also highlights the application of ion-modulation optoelectronic devices in artificial vision systems,neuromorphic computing,and other bionic fields.Finally,the existing challenges and future direc-tions for the development of optoelectronic neuromorphic devices are discussed,providing critical insights for advancing this promising field.
基金supported by the Natural Science Foundation of Zhejiang Province(Grant No.LQ24F040007)the National Natural Science Foundation of China(Grant No.U22A2075)the Opening Project of State Key Laboratory of Polymer Materials Engineering(Sichuan University)(Grant No.sklpme2024-1-21).
文摘To address the increasing demand for massive data storage and processing,brain-inspired neuromorphic comput-ing systems based on artificial synaptic devices have been actively developed in recent years.Among the various materials inves-tigated for the fabrication of synaptic devices,silicon carbide(SiC)has emerged as a preferred choices due to its high electron mobility,superior thermal conductivity,and excellent thermal stability,which exhibits promising potential for neuromorphic applications in harsh environments.In this review,the recent progress in SiC-based synaptic devices is summarized.Firstly,an in-depth discussion is conducted regarding the categories,working mechanisms,and structural designs of these devices.Subse-quently,several application scenarios for SiC-based synaptic devices are presented.Finally,a few perspectives and directions for their future development are outlined.
基金supported by the Hunan Science Fund for Distinguished Young Scholars(2023JJ10069)the National Natural Science Foundation of China(52172169)the Project of State Key Laboratory of Precision Manufacturing for Extreme Service Performance,Central South University(ZZYJKT2024-02).
文摘The traditional von Neumann architecture has demonstrated inefficiencies in parallel computing and adaptive learn-ing,rendering it incapable of meeting the growing demand for efficient and high-speed computing.Neuromorphic comput-ing with significant advantages such as high parallelism and ultra-low power consumption is regarded as a promising pathway to overcome the limitations of conventional computers and achieve the next-generation artificial intelligence.Among various neuromorphic devices,the artificial synapses based on electrolyte-gated transistors stand out due to their low energy consump-tion,multimodal sensing/recording capabilities,and multifunctional integration.Moreover,the emerging optoelectronic neuro-morphic devices which combine the strengths of photonics and electronics have demonstrated substantial potential in the neu-romorphic computing field.Therefore,this article reviews recent advancements in electrolyte-gated optoelectronic neuromor-phic transistors.First,it provides an overview of artificial optoelectronic synapses and neurons,discussing aspects such as device structures,operating mechanisms,and neuromorphic functionalities.Next,the potential applications of optoelectronic synapses in different areas such as artificial visual system,pain system,and tactile perception systems are elaborated.Finally,the current challenges are summarized,and future directions for their developments are proposed.
基金supported by the NSFC(12474071)Natural Science Foundation of Shandong Province(ZR2024YQ051)+5 种基金Open Research Fund of State Key Laboratory of Materials for Integrated Circuits(SKLJC-K2024-12)the Shanghai Sailing Program(23YF1402200,23YF1402400)Funded by Basic Research Program of Jiangsu(BK20240424)Taishan Scholar Foundation of Shandong Province(tsqn202408006)Young Talent of Lifting engineering for Science and Technology in Shandong,China(SDAST2024QTB002)the Qilu Young Scholar Program of Shandong University.
文摘As an emerging memory device,memristor shows great potential in neuromorphic computing applications due to its advantage of low power consumption.This review paper focuses on the application of low-power-based memristors in various aspects.The concept and structure of memristor devices are introduced.The selection of functional materials for low-power memristors is discussed,including ion transport materials,phase change materials,magnetoresistive materials,and ferroelectric materials.Two common types of memristor arrays,1T1R and 1S1R crossbar arrays are introduced,and physical diagrams of edge computing memristor chips are discussed in detail.Potential applications of low-power memristors in advanced multi-value storage,digital logic gates,and analogue neuromorphic computing are summarized.Furthermore,the future challenges and outlook of neuromorphic computing based on memristor are deeply discussed.
基金supported by the Joint R&D Fund of Beijing Smartchip Microelectronics Technology Co.,Ltd.,SGSC0000XSQT2207067.
文摘As traditional von Neumann architectures face limitations in handling the demands of big data and complex computa-tional tasks,neuromorphic computing has emerged as a promising alternative,inspired by the human brain's neural networks.Volatile memristors,particularly Mott and diffusive memristors,have garnered significant attention for their ability to emulate neuronal dynamics,such as spiking and firing patterns,enabling the development of reconfigurable and adaptive computing systems.Recent advancements include the implementation of leaky integrate-and-fire neurons,Hodgkin-Huxley neurons,opto-electronic neurons,and time-surface neurons,all utilizing volatile memristors to achieve efficient,low-power,and highly inte-grated neuromorphic systems.This paper reviews the latest progress in volatile memristor-based artificial neurons,highlight-ing their potential for energy-efficient computing and integration with artificial synapses.We conclude by addressing chal-lenges such as improving memristor reliability and exploring new architectures to advance memristor-based neuromorphic com-puting.
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 Research Foundation of Korea(NRF)Grant funded by the Korea Government(Ministry of Science and ICT)(No.NRF-2022R1A2C2010774)by the GRRC program of Gyeonggi Province(GRRC Sungkyunkwan 2023-B04)by Korea Institute for Advancement of Technology(KIAT)grant funded by the Korea Government(MOTIE)(P0020967,Advanced Training Program for Smart Sensor Engineers).
文摘With the rise of artificial intelligence(AI),neuromorphic sensory systems that emulate the five basic human sensations including tactility,audition,olfaction,gustation,and vision have attracted significant attention.In particular,research on integrating sensors with artificial synapses is being carried out extensively.These studies offer valuable opportunities for making another breakthrough in AI technology,including autonomous systems,real-time monitoring systems,and human-machine interactions.In this review,we introduce promising reports of neuromorphic sensory systems.Specifically,the core sensing material,device architecture,fabrication process,and applications of the proposed systems are presented in detail.Finally,the unsolved challenges and the prospects of neuromorphic sensory systems are discussed.
基金supported by the National Key Research and Development Program of China(2020YFA0714700)Natural Science Foundation of China(62274174)+3 种基金Key Research and Development Program of Jiangsu Province(BK20232009)a fellowship from the China Postdoctoral Science Foundation(NO:2023M742559)the Cooperation Project of Vacuum Interconnect Research Facility(NANO-X)of Suzhou Institute of Nano-Tech and Nano-Bionics,Chinese Academy of Sciences(F2208)the technical support for Nano-X from Suzhou Institute of Nano-Tech and Nano-Bionics,Chinese Academy of Sciences(SINANO)。
文摘Artificial multisensory devices play a key role in human-computer interaction in the field of artificial intelligence(AI).In this work,we have designed and constructed a novel olfactory-visual bimodal neuromorphic carbon nanotube thin film transistor(TFT)arrays for artificial olfactory-visual multisensory synergy recognition with a very low power consumption of 25 aJ for a single pulse,employing semiconducting single-walled carbon nanotubes(sc-SWCNTs)as channel materials and gas sensitive materials,and poly[[4,8-bis[5-(2-ethylhexyl)-2-thienyl]benzo[1,2-b:4,5-b0]dithiophene-2,6-diyl]-2,5-thiophenediyl-[5,7-bis(2-ethylhexyl)-4,8-dioxo-4H,8H-benzo[1,2-c:4,5-c0]dithio-phene-1,3-diyl]](PBDB-T)as the photosensitive material.It is noted that it is the first time to realize the simulation of olfactory and visual senses(from 280 nm to 650 nm)with the wide operating temperature range(0-150℃)in a single SWCNT TFT device and successfully simulate the recovery of olfactory senses after COVID-19 by olfactory-visual synergy.Furthermore,our SWCNT neuromorphic TFT devices with a high IOn/IOff ratio(up to 10^(6))at a low operating voltage(−2 to 0.5 V)can mimic not only the basic biological synaptic functions of olfaction and vision(such as paired-pulse facilitation,short-term plasticity,and long-term plasticity),but also optical wireless communication by Morse code.The proposed multisensory,broadband light-responsive,low-power synaptic devices provide great potential for developing AI robots to face complex external environments.
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supported by the NSFC(12474071)Natural Science Foundation of Shandong Province(ZR2024YQ051)+5 种基金Open Research Fund of State Key Laboratory of Materials for Integrated Circuits(SKLJC-K2024-12)the Shanghai Sailing Program(23YF1402200,23YF1402400)Natural Science Foundation of Jiangsu Province(BK20240424)Taishan Scholar Foundation of Shandong Province(tsqn202408006)Young Talent of Lifting engineering for Science and Technology in Shandong,China(SDAST2024QTB002)the Qilu Young Scholar Program of Shandong University.
文摘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.
基金the financial support from the National Natural Science Foundation of China(62274088,62288102)the Project funded by China Postdoctoral Science Foundation(2023M741657)+1 种基金the Jiangsu Funding Program for Excellent Postdoctoral Talent(2023ZB554)the Jiangsu Specially-Appointed Professor program。
文摘Artificial skin should embody a softly functional film that is capable of self-powering,healing and sensing with neuromorphic processing.However,the pursuit of a bionic skin that combines high flexibility,self-healability,and zero-powered photosynaptic functionality remains elusive.In this study,we report a self-powered and self-healable neuromorphic vision skin,featuring silver nanoparticle-doped ionogel heterostructure as photoacceptor.The localized surface plasmon resonance induced by light in the nanoparticles triggers temperature fluctuations within the heterojunction,facilitating ion migration for visual sensing with synaptic behaviors.The abundant reversible hydrogen bonds in the ionogel endow the skin with remarkable mechanical flexibility and self-healing properties.We assembled a neuromorphic visual skin equipped with a 5×5 photosynapse array,capable of sensing and memorizing diverse light patterns.
基金supported by the National Natural Science Foundation of China(Grant No.62074163)Beijing Natural Science Foundation(Grant No.JQ24030).
文摘Organic electrochemical transistors have emerged as a solution for artificial synapses that mimic the neural functions of the brain structure,holding great potentials to break the bottleneck of von Neumann architectures.However,current artificial synapses rely primarily on electrical signals,and little attention has been paid to the vital role of neurotransmitter-mediated artificial synapses.Dopamine is a key neurotransmitter associated with emotion regulation and cognitive processes that needs to be monitored in real time to advance the development of disease diagnostics and neuroscience.To provide insights into the development of artificial synapses with neurotransmitter involvement,this review proposes three steps towards future biomimic and bioinspired neuromorphic systems.We first summarize OECT-based dopamine detection devices,and then review advances in neurotransmitter-mediated artificial synapses and resultant advanced neuromorphic systems.Finally,by exploring the challenges and opportunities related to such neuromorphic systems,we provide a perspective on the future development of biomimetic and bioinspired neuromorphic systems.
基金supported by National Research Foundation of Korea(NRF)[RS-2024-00350701 and RS-2023-00207828].
文摘To emulate the functionality of the human retina and achieve a neuromorphic visual system,the development of a photonic synapse capable of multispectral color discrimination is of paramount importance.However,attaining robust color discrimination across a wide intensity range,even irrespective of medium limitations in the channel layer,poses a significant challenge.Here,we propose an approach that can bestow the color-discriminating synaptic functionality upon a three-terminal transistor flash memory even with enhanced discriminating capabilities.By incorporating the strong induced dipole moment effect at the excitation,modulated by the wavelength of the incident light,into the floating gate,we achieve outstanding RGB color-discriminating synaptic functionality within a remarkable intensity range spanning from 0.05 to 40 mW cm^(-2).This approach is not restricted to a specific medium in the channel layer,thereby enhancing its applicability.The effectiveness of this color-discriminating synaptic functionality is demonstrated through visual pre-processing of a photonic synapse array,involving the differentiation of RGB channels and the enhancement of image contrast with noise reduction.Consequently,a convolutional neural network can achieve an impressive inference accuracy of over 94%for Canadian-Institute-For-Advanced-Research-10 colorful image recognition task after the pre-processing.Our proposed approach offers a promising solution for achieving robust and versatile RGB color discrimination in photonic synapses,enabling significant advancements in artificial 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(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.
文摘The rapid advancement of deep learning and the emergence of largescale neural models,such as bidirectional encoder representations from transformers(BERT),generative pre-trained transformer(GPT),and large language model Meta AI(LLaMa),have brought significant computational and energy challenges.Neuromorphic computing presents a biologically inspired approach to addressing these issues,leveraging event-driven processing and in-memory computation for enhanced energy efficiency.This survey explores the intersection of neuromorphic computing and large-scale deep learning models,focusing on neuromorphic models,learning methods,and hardware.We highlight transferable techniques from deep learning to neuromorphic computing and examine the memoryrelated scalability limitations of current neuromorphic systems.Furthermore,we identify potential directions to enable neuromorphic systems to meet the growing demands of modern AI workloads.
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the support of the National Natural Science Foundation of China(Grant No.62204201)。
文摘In the past decade,there has been tremendous progress in integrating chalcogenide phase-change materials(PCMs)on the silicon photonic platform for non-volatile memory to neuromorphic in-memory computing applications.In particular,these non von Neumann computational elements and systems benefit from mass manufacturing of silicon photonic integrated circuits(PICs)on 8-inch wafers using a 130 nm complementary metal-oxide semiconductor line.Chip manufacturing based on deep-ultraviolet lithography and electron-beam lithography enables rapid prototyping of PICs,which can be integrated with high-quality PCMs based on the wafer-scale sputtering technique as a back-end-of-line process.In this article,we present an overview of recent advances in waveguide integrated PCM memory cells,functional devices,and neuromorphic systems,with an emphasis on fabrication and integration processes to attain state-of-the-art device performance.After a short overview of PCM based photonic devices,we discuss the materials properties of the functional layer as well as the progress on the light guiding layer,namely,the silicon and germanium waveguide platforms.Next,we discuss the cleanroom fabrication flow of waveguide devices integrated with thin films and nanowires,silicon waveguides and plasmonic microheaters for the electrothermal switching of PCMs and mixed-mode operation.Finally,the fabrication of photonic and photonic–electronic neuromorphic computing systems is reviewed.These systems consist of arrays of PCM memory elements for associative learning,matrix-vector multiplication,and pattern recognition.With large-scale integration,the neuromorphic photonic computing paradigm holds the promise to outperform digital electronic accelerators by taking the advantages of ultra-high bandwidth,high speed,and energy-efficient operation in running machine learning algorithms.
基金supported by the Hunan Science Fund for Distinguished Young Scholars (2023JJ10069)the National Natural Science Foundation of China (52172169)。
文摘Neuromorphic computing systems,which mimic the operation of neurons and synapses in the human brain,are seen as an appealing next-generation computing method due to their strong and efficient computing abilities.Two-dimensional (2D) materials with dangling bond-free surfaces and atomic-level thicknesses have emerged as promising candidates for neuromorphic computing hardware.As a result,2D neuromorphic devices may provide an ideal platform for developing multifunctional neuromorphic applications.Here,we review the recent neuromorphic devices based on 2D material and their multifunctional applications.The synthesis and next micro–nano fabrication methods of 2D materials and their heterostructures are first introduced.The recent advances of neuromorphic 2D devices are discussed in detail using different operating principles.More importantly,we present a review of emerging multifunctional neuromorphic applications,including neuromorphic visual,auditory,tactile,and nociceptive systems based on 2D devices.In the end,we discuss the problems and methods for 2D neuromorphic device developments in the future.This paper will give insights into designing 2D neuromorphic devices and applying them to the future neuromorphic systems.
