A Reliable All-2D Materials Artificial Synapse for High Energy-Efficient Neuromorphic Computing

Tang Jian; He Congli; Tang Jianshi; Yue Kun; Zhang Qingtian; Liu Yizhou; Wang Qinqin; Wang Shuopei; Li Na; Shen Cheng; Zhao Yanchong; Liu Jieying; Yuan Jiahao; Wei Zheng; Li Jiawei; Watanabe Kenji; Taniguchi Takashi; Shang Dashan; Wang Shouguo; Yang Wei; Yang Rong; Shi Dongxia; Zhang Guangyu

首页> 外文期刊>Advanced Functional Materials >A Reliable All-2D Materials Artificial Synapse for High Energy-Efficient Neuromorphic Computing

【24h】

A Reliable All-2D Materials Artificial Synapse for High Energy-Efficient Neuromorphic Computing

机译：一种可靠的全2D材料人工突触，用于高能效性神经形态计算

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

High-performance artificial synaptic devices are indispensable for developing neuromorphic computing systems with high energy efficiency. However, the reliability and variability issues of existing devices such as nonlinear and asymmetric weight update are the major hurdles in their practical applications for energy-efficient neuromorphic computing. Here, a two-terminal floating-gate memory (2TFGM) based artificial synapse built from all-2D van der Waals materials is reported. The 2TFGM synaptic device exhibits excellent linear and symmetric weight update characteristics with high reliability and tunability. In particular, the high linearity and symmetric synaptic weight realized by simple programming with identical pulses can eliminate the additional latency and power consumption caused by the peripheral circuit design and achieve an ultralow energy consumption for the synapses in the neural network implementation. A large number of states up to approximate to 3000, high switching speed of 40 ns and low energy consumption of 18 fJ for a single pulse have been demonstrated experimentally. A high classification accuracy up to 97.7% (close to the software baseline of 98%) has been achieved in the Modified National Institute of Standards and Technology (MNIST) simulations based on the experimental data. These results demonstrate the potential of all-2D 2TFGM for high-speed and low-power neuromorphic computing.

机译：高性能人工突触装置是开发具有高能量效率的神经形态计算系统必不可少的。然而，现有设备的可靠性和可变性问题如非线性和不对称权重更新是其实际应用中的主要障碍，以节能神经形态计算。这里，报道了由All-2D范德瓦尔斯材料构建的基于两端的浮栅存储器（2TFGM）的人工突触。 2TFGM突触装置具有高可靠性和可调性的优异的线性和对称重量更新特性。特别地，通过具有相同脉冲的简单编程实现的高线性和对称突触重量可以消除由外围电路设计引起的额外延迟和功耗，并实现神经网络实现中的突触的超级能耗。实验证明了大量达到3000°的近似近似3000，40 ns的高开关速度和18 fj的低能量消耗。基于实验数据，在修改的国家标准和技术研究所（MNIST）模拟中，高达97.7％的高度分类准确性（靠近98％的软件基线）已经实现。这些结果证明了全-2D 2TFGM用于高速和低功率神经形态计算的潜力。

著录项

来源
《Advanced Functional Materials》 |2021年第27期|2011083.1-2011083.9|共9页
作者
Tang Jian; He Congli; Tang Jianshi; Yue Kun; Zhang Qingtian; Liu Yizhou; Wang Qinqin; Wang Shuopei; Li Na; Shen Cheng; Zhao Yanchong; Liu Jieying; Yuan Jiahao; Wei Zheng; Li Jiawei; Watanabe Kenji; Taniguchi Takashi; Shang Dashan; Wang Shouguo; Yang Wei; Yang Rong; Shi Dongxia; Zhang Guangyu;
展开▼
作者单位

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Phys Sci Beijing 100190 Peoples R China;

Beijing Normal Univ Inst Adv Mat Beijing 100875 Peoples R China;

Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol BNRis Inst Microelect Beijing 100084 Peoples R China|Tsinghua Univ Beijing Innovat Ctr Future Chips ICFC Beijing 100084 Peoples R China;

Univ Southern Calif Ming Hsieh Dept Elect Engn Los Angeles CA 90089 USA;

Tsinghua Univ Beijing Innovat Ctr Future Chips ICFC Beijing 100084 Peoples R China;

RIKEN Ctr Emergent Matter Sci CEMS Wako Saitama 3510198 Japan;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Phys Sci Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Phys Sci Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Phys Sci Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Phys Sci Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Phys Sci Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Phys Sci Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Phys Sci Beijing 100190 Peoples R China;

Beijing Normal Univ Inst Adv Mat Beijing 100875 Peoples R China|Univ Chinese Acad Sci Sch Phys Sci Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Phys Sci Beijing 100190 Peoples R China;

Chinese Acad Sci Beijing Natl Lab Condensed Matter Phys Inst Phys Key Lab Nanoscale Phys & Devices Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Phys Sci Beijing 100190 Peoples R China;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
2D materials; artificial synapse; linear weight update; MoS; (2);

机译：2D材料;人工突触;线性重量更新;MOS;（2）;

相似文献

外文文献
中文文献
专利

1. Emerging Memristive Artificial Synapses and Neurons for Energy-Efficient Neuromorphic Computing [J] . Choi Sanghyeon, Yang Jehyeon, Wang Gunuk Advanced Materials . 2020,第51期

机译：新兴椎间膜人工突触和神经元用于节能神经形态计算
2. Memristors Based on 2D Materials as an Artificial Synapse for Neuromorphic Electronics [J] . Huh Woong, Lee Donghun, Lee Chul-Ho Advanced Materials . 2020,第51期

机译：基于2D材料作为神经形态电子人工突触的忆耳
3. An air-stable artificial synapse based on a lead-free double perovskite Cs2AgBiBr6 film for neuromorphic computing [J] . Lao Jie, Xu Wen, Jiang Chunli, Journal of Materials Chemistry, C. materials for optical and electronic devices . 2021,第17期

机译：基于无铅双钙钛矿CS2AGBIBR6薄膜的空气稳定的人工突触，用于神经形态计算
4. (Invited) Capturing Biological Behavior in Nanomagnetic Artificial Neurons and Synapses for Energy-Efficient Neuromorphic Computing [C] . Jean Anne C Incorvia, Joseph S Friedman, Matthew J. Marinella, Pacific Rim Meeting on Electrochemical and Solid-State Science . 2020

机译：（邀请）捕获纳米磁性神经元的生物行为和节能神经形态计算的突触
5. Modeling and optimization of high-performance many-core systems for energy-efficient and reliable computing. [D] . Meng, Jie. 2013

机译：高性能多核系统的建模和优化，以实现节能高效和可靠的计算。
6. Temperature-resilient solid-state organic artificial synapses for neuromorphic computing [O] . A. Melianas, T. J. Quill, G. LeCroy, 2020

机译：温度 - 弹性固态有机人工突触的神经形态计算
7. Artificial Synapses: Dimensionality Dependent Plasticity in Halide Perovskite Artificial Synapses for Neuromorphic Computing (Adv. Electron. Mater. 9/2019) [O] . Sung‐Il Kim, Yeongjun Lee, Min‐Ho Park, 2019

机译：人工突触：卤化物钙术中的维度依赖性可塑性神经形态计算的人工突触（ADV。电子。Matter。9/2019）

A Reliable All-2D Materials Artificial Synapse for High Energy-Efficient Neuromorphic Computing

摘要

著录项

相似文献

相关主题

期刊订阅