Generation of STDP With Non-Volatile Tunnel-FET Memory for Large-Scale and Low-Power Spiking Neural Networks

Generation of STDP With Non-Volatile Tunnel-FET Memory for Large-Scale and Low-Power Spiking Neural Networks
复制标题

使用非易失性隧道 FET 存储器生成 STDP,用于大规模和低功耗尖峰神经网络

DOI:
10.1109/jeds.2020.3025336
复制
发表时间:
2020
影响因子:
2.3
通讯作者:
Tanaka Tetsu
Tanaka Tetsu
中科院分区:
工程技术3区
文献类型:
--
作者:
Kino Hisashi;Fukushima Takafumi;Tanaka Tetsu

文献摘要

参考文献

相似文献

脉冲神经网络作为下一代神经网络已经引起了广泛的关注。由于SNN由具有尖峰定时相关可塑性(STDP)特性的设备组成,因此STDP是我们实现SNN需要考虑的关键特性之一。在这项研究中,我们产生的STDP的生物突触与非易失性隧道场效应晶体管(隧道FET)的存储器,具有电荷存储层和隧道FET结构。隧道场效应晶体管由于其陡峭的亚阈值斜率,是一种很有前途的降低工作电压的结构。因此,我们提出的非易失性隧道FET存储器能够实现低操作电压SNN。本文报道了具有p沟道MOS型操作的非易失性隧道FET存储器的I-V特性、编程特性以及对称和非对称STDP特性。
Spiking neural networks (SNNs) have attracted considerable attention as next-generation neural networks. As SNNs consist of devices that have spike-timing-dependent plasticity (STDP) characteristics, STDP is one of the critical characteristics we need to consider to implement an SNN. In this study, we generated the STDP of a biological synapse with non-volatile tunnel-field-effect-transistor (tunnel FET) memory that has a charge-storage layer and a tunnel FET structure. Tunnel FET is a promising structure to reduce the operation voltage owing to its steep sub-threshold slope. Therefore, the non-volatile tunnel-FET memory we propose enables the implementation of low-operation-voltage SNNs. This article reports the I-V, programming, and both symmetric and asymmetric STDP characteristics of a non-volatile tunnel-FET memory with p-channel-MOS-like operation.
浮栅突触中的鲁棒双态 STDP
DOI: 10.1109/ijcnn.2014.6889631
发表时间: 2014
期刊: 2014 International Joint Conference on Neural Networks (IJCNN)
影响因子: --
作者:
Roshan Gopalakrishnan;A. Basu
通讯作者: A. Basu
DOI: 10.35848/1347-4065/ab6867
发表时间: 2020-02
影响因子: 1.5
作者:
H. Kino;T. Fukusima;Tetsu Tanaka
通讯作者: H. Kino;T. Fukusima;Tetsu Tanaka
具有陡峭亚阈值斜率和大存储窗口的隧道场效应晶体管电荷捕获存储器
DOI: 10.7567/jjap.57.04fe07
发表时间: 2018
影响因子: 1.5
作者:
H. Kino;T. Fukushima;Tetsu Tanaka
通讯作者: Tetsu Tanaka
DOI: 10.35848/1882-0786/ab9875
发表时间: 2020
影响因子: 2.3
作者:
Kimihiko Kato;T. Mori;Y. Morita;T. Matsukawa;M. Takenaka;S. Takagi
通讯作者: S. Takagi
提高基于 ReRAM 的具有随机尖峰时序相关可塑性的尖峰神经网络加速器的鲁棒性
DOI: --
发表时间: 2019
期刊: International Join Conference on Neural Network
影响因子: --
作者:
She, Xueyuan;Long, Yun;Mukhopadhyay, Saibal.
通讯作者: Mukhopadhyay, Saibal.