Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

MOS Capacitor

MOS Capacitor

A Metal-Oxide-Semiconductor (MOS) capacitor is a fundamental structure used extensively in semiconductor device technology, particularly in the fabrication of integrated circuits and MOSFETs (metal-oxide-semiconductor field-effect transistors). The MOS capacitor consists of three layers: a metal gate, a dielectric oxide, and a semiconductor substrate.
The metal gate is typically made from highly conductive materials such as aluminum or polysilicon. Beneath the metal gate lies a thin layer of...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Tunable and Selective Doping Modulation in Pd-Filled Carbon Nanotube Transistors.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

Imaging Multistep s‑Triazine Oligomerization via Cobalt-Assisted Deamination and Selective C-C Coupling.

Precision chemistry·2026

Same author

Broad-Spectrum Absorption and Microsecond Excited State in Copper-MOFs for Boosting Organic Photosynthesis.

Journal of the American Chemical Society·2026

Same author

A non-van der Waals platform for deep-subwavelength twist-polaritonics based on β-Ga<sub>2</sub>O<sub>3</sub> nanoflakes.

Nanoscale horizons·2026

Same author

Regulating the Electronic Structures of Co Sites in Salen Cobalt Complexes for Boosting CO<sub>2</sub> Photoreduction.

Inorganic chemistry·2026

Same author

Controllable Formation of Threefold-Coordinated Oxygen in Graphene by Low-Energy Ion Implantation.

Nano letters·2026

Search research articles

相关实验视频

Updated: Jan 17, 2026

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

一个可重新配置的光敏分离浮动门内存用于神经形态计算和非线性激活.

Zhi-Cheng Zhang¹, Yuan Li¹, Jian Yao²

¹The Key Laboratory of Weak Light Nonlinear Photonics, Ministry of Education, School of Physics, Nankai University, Tianjin, China.

Nature communications

|January 14, 2026

概括

此摘要是机器生成的。

研究人员开发了一种用于人工智能 (AI) 和物联网 (IoT) 应用的新型分裂浮动门内存设备. 这种紧,可重新配置的硬件将传感,计算和非线性处理统一为高效的智能系统.

更多相关视频

In Situ Transmission Electron Microscopy with Biasing and Fabrication of Asymmetric Crossbars Based on Mixed-Phased a-VOx

In Situ Transmission Electron Microscopy with Biasing and Fabrication of Asymmetric Crossbars Based on Mixed-Phased a-VOx

Published on: May 13, 2020

A Method for Growing Bio-memristors from Slime Mold

A Method for Growing Bio-memristors from Slime Mold

Published on: November 2, 2017

相关实验视频

Last Updated: Jan 17, 2026

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

In Situ Transmission Electron Microscopy with Biasing and Fabrication of Asymmetric Crossbars Based on Mixed-Phased a-VOx

In Situ Transmission Electron Microscopy with Biasing and Fabrication of Asymmetric Crossbars Based on Mixed-Phased a-VOx

Published on: May 13, 2020

A Method for Growing Bio-memristors from Slime Mold

A Method for Growing Bio-memristors from Slime Mold

Published on: November 2, 2017

科学领域:

* 材料科学与工程 * 材料科学与工程
* 神经形态计算是一种神经形态计算.
* 人工智能硬件硬件

背景情况:

*人工智能 (AI) 和物联网 (IoT) 的扩张需要能够集成传感,计算和非线性处理的紧硬件.
*当前的神经形态系统往往受限于功能,依赖于异质集成,阻碍了可扩展性和效率.

研究的目的:

* 推出一种新的多式联络分开浮动门记忆装置.
* 在一个单一的设备内展示传感器内计算,内存计算和多个非线性激活函数的单一集成.
*为可扩展,节能智能系统建立硬件基础.

主要方法:

*开发了一种高速,可重新配置的多模式分割浮动门内存架构.
* 在空间分离的浮动门中对电荷进行编程,以控制光响应性和导电性.
* 整形的电气重新配置以模拟ReLU和Sigmoid激活功能.
* 实现完全基于硬件的传感器处理器系统,使用内存阵列进行学习任务.

主要成果:

* 该设备单体集成传感,内存计算和多个非线性激活功能 (ReLU,Sigmoid).
*通过充电编程实现光响应性和导电性的非挥发性模拟控制.
* 一个完整的传感器处理器系统成功地在硬件中执行了无监督和监督的学习任务.
* 证明了高速和可重新配置的操作.

结论:

*开发的分裂浮动门内存为智能系统提供了紧而节能的解决方案.
* 多种功能的单体集成增强了与现有的神经形态方法相比的可扩展性和效率.
* 这项技术为下一代人工智能和物联网应用提供了可重新配置的硬件基础.