检索结果-南通市图书馆

One memristor–one electrolyte-gated transistor-based high energy-efficient dropout neuronal units

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第6期33卷 569-573页

作者：李亚霖时凯璐朱一新方晓崔航源万青万昌锦 School of Electronic Science&Engineering and Collaborative Innovation Center of Advanced MicrostructuresNanjing UniversityNanjing 210023China Yongjiang Laboratory(Y-LAB) Ningbo 315202China

Artificial neural networks(ANN) have been extensively researched due to their significant energy-saving *** implementations of ANN with dropout function would be able to avoid the overfitting problem. This letter reports a dropout neuronal unit(1R1T-DNU) based on one memristor–one electrolyte-gated transistor with an ultralow energy consumption of 25 p J/spike. A dropout neural network is constructed based on such a device and has been verified by MNIST dataset, demonstrating high recognition accuracies(> 90%) within a large range of dropout probabilities up to40%. The running time can be reduced by increasing dropout probability without a significant loss in accuracy. Our results indicate the great potential of introducing such 1R1T-DNUs in full-hardware neural networks to enhance energy efficiency and to solve the overfitting problem.

关键词： dropout neuronal unit synaptic transistors memristor artificial neural network

IGZO-based neuromorphic transistors with temperature-dependent synaptic plasticity and spiking logics

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2022年第6期65卷 218-225页

作者： Ying ZHU Yongli HE Chunsheng CHEN Li ZHU changjin wan Qing wan School of Electronic & Science Engineering and Collaborative Innovation Center of Advanced Microstructures Nanjing University

Temperature is one of the vital influential factors for all physiological and mental *** the influence of temperature on the properties of synaptic devices is of great importance for neuromorphic computing and bionic perception. Here, indium-gallium-zinc-oxide(IGZO) based electrical-doublelayer neuromorphic transistors were proposed for the emulation of temperature-dependent synaptic *** influence of temperature on the synaptic plasticity, including excitatory postsynaptic current, pairedpulse facilitation, and dynamic filtering was investigated. Interestingly, temperature induced spiking AND to OR logic switching was demonstrated in an IGZO-based neuromorphic transistor with two in-plane gate electrodes. Our results provided an insight into the temperature-induced synaptic functions and spiking logic switching, which is interesting for neuromorphic systems with biological fidelity.

关键词： neuromorphic transistors IGZO TFTs temperature-dependent synaptic plasticity logic transformation

CMOS-compatible neuromorphic devices for neuromorphic perception and computing: a review

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

International Journal of Extreme Manufacturing 2023年第4期5卷 292-312页

作者： Yixin Zhu Huiwu Mao Ying Zhu Xiangjing wang Chuanyu Fu Shuo Ke changjin wan Qing wan School of Electronic Science and Engineering and Collaborative Innovation Center of Advanced MicrostructuresNanjing UniversityNanjing 210023People’s Republic of China Yongjiang Lab Ningbo 315201People’s Republic of China School of Micro-Nano Electronics Hangzhou Global Scientific and Technological Innovation CentreZhejiang University38 Zheda RoadHangzhou 310027People’s Republic of China

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 *** 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 *** types of neuromorphic devices have been proposed based on different physical mechanisms such as resistive switching devices and electric-double-layer *** devices have demonstrated a range of neuromorphic functions such as multistate storage,spike-timing-dependent plasticity,dynamic filtering,*** achieve high performance neuromorphic computing systems,it is essential to fabricate neuromorphic devices compatible with the complementary metal oxide semiconductor(CMOS)manufacturing *** improves the device’s reliability and stability and is favorable for achieving neuromorphic chips with higher integration density and low power *** review summarizes CMOS-compatible neuromorphic devices and discusses their emulation of synaptic and neuronal functions as well as their applications in neuromorphic perception and *** highlight challenges and opportunities for further development of CMOS-compatible neuromorphic devices and systems.

关键词： neuromorphic computing neuromorphic devices CMOS-compatible resistive switching device transistor

High-Performance Indium-Gallium-Zinc-Oxide Thin-Film Transistors with Stacked Al_(2)O_(3)/HfO_(2) Dielectrics

在线全文

学校读者我要写书评

暂无评论

Chinese Physics Letters 2022年第11期39卷 68-71页

作者： Yue Li Li Zhu Chunsheng Chen Ying Zhu changjin wan Qing wan School of Electronic Science and Engineering Nanjing UniversityNanjing 210093China

High-performance amorphous indium-gallium-zinc-oxide thin-film transistors(a-IGZO TFTs)gated by AlO/HfOstacked dielectric films are *** optimized TFTs with AlO(2.0 nm)/HfO(13 nm)stacked gate dielectrics demonstrate the best performance,including low total trap density Nt,low subthreshold swing voltage,large switching ratio I/,high mobilityμ,and low operating voltage,equal to 1.35×10cm,88 mV/dec,5.24×10~8,14.2 cm~2/V·s,and 2.0 V,***,a low-voltage-operated resistor-loaded inverter has been fabricated based on such an a-IGZO TFT,showing ideal full swing characteristics and high gain of~27 at 3.0 *** results indicate a-IGZO TFTs gated by optimized AlO/HfOstacked dielectrics are of great interests for low-power,high performance,and large-area display and emerging electronics.

关键词： Zinc inverter performance

Indium-Gallium-Zinc-Oxide-Based Photoelectric Neuromorphic Transistors for Spiking Morse Coding

在线全文

学校读者我要写书评

暂无评论

Chinese Physics Letters 2022年第6期39卷 1-4页

作者： Xinhuang Lin Haotian Long Shuo Ke Yuyuan wang Ying Zhu Chunsheng Chen changjin wan Qing wan School of Electronic Science and Engineering Nanjing UniversityNanjing 210093China

The human brain that relies on neural networks communicated by spikes is featured with ultralow energy consumption, which is more robust and adaptive than any digital system. Inspired by the spiking framework of the brain, spike-based neuromorphic systems have recently inspired intensive attention. Therefore, neuromorphic devices with spike-based synaptic functions are considered as the first step toward this aim. Photoelectric neuromorphic devices are promising candidates for spike-based synaptic devices with low latency, broad bandwidth,and superior parallelism. Here, the indium-gallium-zinc-oxide-based photoelectric neuromorphic transistors are fabricated for Morse coding based on spike processing, 405-nm light spikes are used as synaptic inputs, and some essential synaptic plasticity, including excitatory postsynaptic current, short-term plasticity, and high-pass filtering, can be mimicked. More interestingly, Morse codes encoded by light spikes are decoded using our devices and translated into amplitudes. Furthermore, such devices are compatible with standard integrated processes suitable for large-scale integrated neuromorphic systems.

关键词： Morse Zinc filtering

2D Material Chemistry:Graphdiyne-based Biochemical Sensing

在线全文

学校读者我要写书评

暂无评论

Chemical Research in Chinese Universities 2020年第4期36卷 622-630页

作者： LI Jiaofu wan changjin wanG Cong ZHANG Han CHEN Xiaodong College of Physics and Optoelectronic Engineering Shenzhen UniversityShenzhen 518060P.R.China Innovative Centre for Flexible Devices(iFLEX) Max Planck-NTU Joint Lab for Artificial SensesSchool of Materials Science and EngineeringNanvang Technological University50 Nanyang AvenueSingapore 639798Singapore

The modern internet-of-things era has witnessed an increasing growth in the demand for advanced sensors to collect precise *** meet this demand,extensive efforts have been devoted to exploring competent ma terials and designing rational architectures for the fabrication of sensing *** represents a promising material due to the attractive *** and electrochemical properties deriving from its unique molecular *** this review,we firstly provide the points of view on the architectures and work principles of the graph divnebased sensing devices with respect to resistive,electrochemical,photoelectrochemical and fluorescent catego ***,we present the promising applications on biochemical sensing,such as the detection of DNA,micro-RNA,and ***,the challenges and prospects of graphdivne-based biochemical sensing platforms are also discussed,in order to provide a cornerstone for understanding this rapidly developing area.

关键词： Graphdiyne 2D material Electrochemical Biochemical sensing Surface chemistry

基于Al_(2)O_(3)/Chitosan叠层栅介质的双栅IGZO神经形态晶体管

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

无机材料学报 2023年第4期38卷 445-451页

作者：王靖瑜万昌锦万青南京大学电子科学与工程学院南京210093 浙江大学微纳电子学院杭州310027

基于铟镓锌氧(IGZO)的双电层(EDL)晶体管以低加工温度、良好的一致性以及丰富的离子动力学等优势,在神经形态感知和计算系统中具有极大的潜在应用前景。然而,双电层IGZO晶体管的高漏电(>10 nA)导致的高能耗以及异常电流尖峰/毛刺一直是... 详细信息

基于铟镓锌氧(IGZO)的双电层(EDL)晶体管以低加工温度、良好的一致性以及丰富的离子动力学等优势,在神经形态感知和计算系统中具有极大的潜在应用前景。然而,双电层IGZO晶体管的高漏电(>10 nA)导致的高能耗以及异常电流尖峰/毛刺一直是相关神经形态计算发展的主要障碍之一。本研究提出了一种具有Al_(2)O_(3)/壳聚糖(Chitosan)叠层栅介质的新型IGZO神经形态晶体管。与单层壳聚糖栅介质晶体管相比,引入Al_(2)O_(3)叠层的器件具有78.3 mV/decade的低亚阈值摆幅,在1.8 V电压下1.3 nA的低漏电流(降低约98%),3.73 V的大滞回窗口(提升3.4倍)以及0.86 nA的低兴奋性突触后电流(降低约97%),单脉冲(0.5 V,20 ms)功耗仅为1.7 pJ(降低约96%)。此外,研究还基于双栅EDL协同调控实现了尖峰突触功能的模拟和沟道电流的有效调制,并有效规避突触塑性模拟中高漏电导致的非正常电流尖峰/毛刺。上述结果表明,堆叠高k栅介质可以有效改善神经形态器件的漏电、功耗和性能,为进一步开发超低功耗神经形态感知和计算系统提供了新的思路。

关键词：神经形态器件 IGZO晶体管人造突触叠层栅介质高k栅介质突触可塑性

在线全文

学校读者我要写书评

暂无评论

柔性神经形态晶体管研究进展

无机材料学报 2023年第4期38卷 367-377页

作者：杨洋崔航源祝影万昌锦万青南京大学电子科学与工程学院南京210023

近年来,受人脑独特工作模式的启发,利用人工神经形态器件模拟突触和神经元的感知与计算功能吸引了广泛关注。到目前为止,已经有很多关于神经形态晶体管的报道,但绝大多数器件是在刚性衬底上加工的。柔性神经形态晶体管不仅可以同时实现... 详细信息

近年来,受人脑独特工作模式的启发,利用人工神经形态器件模拟突触和神经元的感知与计算功能吸引了广泛关注。到目前为止,已经有很多关于神经形态晶体管的报道,但绝大多数器件是在刚性衬底上加工的。柔性神经形态晶体管不仅可以同时实现信号传输和训练学习,对多路信号进行非线性的时空整合与协同调控,而且能密切贴合柔软的人体皮肤,承受器官和组织的高生理应变。更重要的是,柔性神经形态晶体管具有可设计的灵活性和优异的生物兼容性,在检测生物环境中生理相关时间尺度的低幅信号方面具备独特的优势和应用潜力。柔性神经形态晶体管已经广泛应用于电子皮肤、人工视觉系统、智能可穿戴系统等领域。目前,研制低功耗、高密度集成的柔性神经形态晶体管是研究的首要任务之一。本文综述了基于不同柔性衬底的神经形态晶体管的研究进展,并展望了柔性神经形态晶体管的未来应用前景,这将为未来柔性神经晶体管的研制以及智能计算和感知应用提供比较详实的参考。

关键词：神经形态器件柔性电子学神经形态晶体管类脑感知与计算综述

在线全文

学校读者我要写书评

暂无评论

超低功耗尖峰视锥感受器及其颜色感知应用

科学通报 2023年第35期68卷 4751-4753页

作者：王祥静万昌锦万青南京大学电子科学与工程学院南京210023

传统机器视觉依赖于CMOS/CCD图像传感器获取视觉信息,并依赖于冯·诺依曼架构的计算机处理这些信息.这种信息获取模式是由人工创建的同步计时和控制信号进行驱动和控制的,这些人工创建的信号与视觉信息的来源及其动态没有任何关联性,因... 详细信息

传统机器视觉依赖于CMOS/CCD图像传感器获取视觉信息,并依赖于冯·诺依曼架构的计算机处理这些信息.这种信息获取模式是由人工创建的同步计时和控制信号进行驱动和控制的,这些人工创建的信号与视觉信息的来源及其动态没有任何关联性,因而包含大量的低特征密度的信息.而生物系统中视觉的形成是由视网膜上的光感受器接收光强和颜色信息,并将其转化为尖峰电位传入视神经且送至大脑的视觉皮层进行感知处理[1].

关键词：颜色信息机器视觉超低功耗 CCD图像传感器冯·诺依曼控制信号视觉信息光感受器