Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Atomic Nuclei: Nuclear Spin State Overview01:03

Atomic Nuclei: Nuclear Spin State Overview

1.2K
NMR-active nuclei have energy levels called 'spin states' that are associated with the orientations of their nuclear magnetic moments. In the absence of a magnetic field, the nuclear magnetic moments are randomly oriented, and the spin states are degenerate. When an external magnetic field is applied, the spin states have only 2 + 1 orientations available to them. A proton with = ½ has two available orientations. Similarly, for a quadrupolar nucleus with a nuclear spin value of...
1.2K
The Role of Ion Channels in Neuronal Computation01:19

The Role of Ion Channels in Neuronal Computation

3.3K
A postsynaptic neuron usually receives numerous impulses from several other presynaptic neurons. The axon hillock of the postsynaptic neuron integrates all these signals and determines the likelihood of firing an action potential.
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
3.3K
Neural Circuits01:25

Neural Circuits

1.6K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.6K
Atomic Nuclei: Nuclear Spin State Population Distribution01:14

Atomic Nuclei: Nuclear Spin State Population Distribution

1.2K
Near absolute zero temperatures, in the presence of a magnetic field, the majority of nuclei prefer the lower energy spin-up state to the higher energy spin-down state. As temperatures increase, the energy from thermal collisions distributes the spins more equally between the two states. The Boltzmann distribution equation gives the ratio of the number of spins predicted in the spin −½ (N−) and spin +½ (N+) states.
1.2K
Atomic Nuclei: Nuclear Spin01:08

Atomic Nuclei: Nuclear Spin

3.2K
All atomic particles possess an intrinsic angular momentum, or 'spin'. Electrons, protons, and neutrons each have a spin value of ½, although protons and neutrons in nuclei may have higher half-integer spins owing to energetic factors.
Atomic nuclei have a net nuclear spin, , which can have an integer or half-integer value. In atomic nuclei, the spins of protons are paired against each other but not with neutrons, and vice versa. Consequently, an even number of protons does not...
3.2K
Spin–Spin Coupling Constant: Overview01:08

Spin–Spin Coupling Constant: Overview

1.0K
In bromoethane, the three methyl protons are coupled to the two methylene protons that are three bonds away. In accordance with the n+1 rule, the signal from the methyl protons is split into three peaks with 1:2:1 relative intensities. The methylene protons appear as a quartet, with the relative intensities of 1:3:3:1.
Qualitatively, any spin plus-half nucleus polarizes the spins of its electrons to the minus-half state. Consequently, the paired electron in the hydrogen–carbon bond must...
1.0K

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

Coherent quantum control of nitrogen vacancy spin with nanoscale magnets.

Nature communications·2026
Same author

Strain Mediated Voltage Control of Magnetic Anisotropy and Magnetization Reversal in Bismuth-Substituted Yttrium Iron Garnet Films and Mesostructures.

ACS applied materials & interfaces·2025
Same author

Magneto-Ionic Physical Reservoir Computing in Perpendicularly Magnetized Heterostructures.

Nano letters·2025
Same author

Self-assembled 3D Interconnected Magnetic Nanowire Networks for Neuromorphic Computing.

ACS applied materials & interfaces·2025
Same author

Antiferromagnetic skyrmion-based energy-efficient leaky integrate and fire neuron device.

Nanotechnology·2025
Same author

Electrically Controlled All-Antiferromagnetic Tunnel Junctions on Silicon with Large Room-Temperature Magnetoresistance.

Advanced materials (Deerfield Beach, Fla.)·2024

相关实验视频

Updated: Sep 19, 2025

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

671

量子化人工神经网络与自旋电子随机计算实现.

Saadi Sabyasachi1, Walid Al Misba1, Yixin Shao2

  • 1Department of Mechanical and Nuclear Engineering, Virginia Commonwealth University, Richmond, VA 23284, United States of America.

Nanotechnology
|June 8, 2025
PubMed
概括

量子化随机计算 (SC) 使用随机磁道连接 (s-MTJs) 显著降低了人工神经网络 (ANN) 的能耗和延迟,同时保持了高精度. 这种方法优化了资源密集的矩阵向量乘法,以实现高效的硬件实现.

关键词:
深度神经网络是一个神经网络.磁道连接点 (MTJ) 是指磁道连接点.定量化定量化是什么随机计算中的随机计算.

更多相关视频

Silicon Metal-oxide-semiconductor Quantum Dots for Single-electron Pumping
14:58

Silicon Metal-oxide-semiconductor Quantum Dots for Single-electron Pumping

Published on: June 3, 2015

14.9K
Nanofabrication of Gate-defined GaAs/AlGaAs Lateral Quantum Dots
15:47

Nanofabrication of Gate-defined GaAs/AlGaAs Lateral Quantum Dots

Published on: November 1, 2013

16.4K

相关实验视频

Last Updated: Sep 19, 2025

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

671
Silicon Metal-oxide-semiconductor Quantum Dots for Single-electron Pumping
14:58

Silicon Metal-oxide-semiconductor Quantum Dots for Single-electron Pumping

Published on: June 3, 2015

14.9K
Nanofabrication of Gate-defined GaAs/AlGaAs Lateral Quantum Dots
15:47

Nanofabrication of Gate-defined GaAs/AlGaAs Lateral Quantum Dots

Published on: November 1, 2013

16.4K

科学领域:

  • * 计算机科学 计算机科学
  • * 电气工程 电气工程
  • * 材料科学 材料科学

背景情况:

  • *人工神经网络 (ANN) 推断需要大量的能量和设备资源,因为矩阵向量乘法.
  • * 随机计算 (SC) 为ANN提供了一个有希望的,资源密集度较低的替代方案,利用随机数生成器 (RNG).
  • * 随机磁道连接 (s-MTJs) 可以为基于硬件的SC生成随机位流,但之前的工作集中在模拟权重上.

研究的目的:

  • * 为了研究SC对矩阵向量乘法与定量化突触权重和输出的有效性.
  • * 用实验性s-MTJ比特流和离散重量/节点状态来评估量子化SC-ANN的性能.
  • * 为了比较量子化SC-ANNs与模拟实现的能源消耗,延迟和准确性.

主要方法:

  • * 实现了量子化SC-ANN,用于权重和隐藏层节点的5个和11个离散状态.
  • *利用实验获得的不同长度 (100-500位) 的s-MTJ比特流.
  • *在MNIST数据集上使用神经网络进行训练和推断,使用一个和三个隐藏层的神经网络.

主要成果:

  • *与模拟s-MTJ ANNs相比,量子化SC-ANNs显示了降低的延迟 (9×) 和能源消耗 (2.6×).
  • *与SC进行训练,在所有配置中始终提高了准确性.
  • *用400位随机位流和三个隐藏层实现了96.82%的峰值精度.

结论:

  • *量子化SC-ANN有效降低硬件资源需求,提高能源效率.
  • * 在SC-ANNs中使用离散量子化状态可以保持准确性,同时提高性能.
  • * 这种方法为使用s-MTJs实现的节能,高性能ANN提供了可行的途径.