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

The Role of Ion Channels in Neuronal Computation01:19

The Role of Ion Channels in Neuronal Computation

4.1K
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....
4.1K
Neural Circuits01:25

Neural Circuits

3.1K
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...
3.1K
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

1.1K
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
1.1K
Neuronal Communication01:28

Neuronal Communication

4.2K
Neurons, the fundamental units of the brain and nervous system, communicate through complex electrochemical signals that underpin all cognitive and bodily functions. This communication is primarily facilitated by a process involving the generation and propagation of an action potential along the axon of the neuron. When the internal electrical charge of a neuron surpasses a certain threshold, an action potential is triggered. This rapid change in voltage travels swiftly along the axon to the...
4.2K
Integration of Synaptic Events01:28

Integration of Synaptic Events

5.5K
Synaptic integration mainly includes the summation of graded potentials. Graded potentials, regardless of their type, cause subtle alterations in membrane voltage, resulting in either depolarization or hyperpolarization. These incremental changes, when combined or summed, can propel the neuron toward its threshold. Consider, for example, a membrane experiencing a +15 mV shift, causing it to depolarize from -70 mV to -55 mV. In this scenario, graded potentials govern the membrane's ability to...
5.5K
Superposition Theorem01:18

Superposition Theorem

1.6K
The superposition principle is a fundamental concept stating that in a linear circuit, the voltage across (or current through) an element can be determined by summing the individual contributions of each independent source acting in isolation. When dealing with linear circuits containing multiple independent sources, this principle serves as a valuable tool for analysis. To apply the superposition principle effectively, one should focus on a single independent source at a time while...
1.6K

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

Enhanced Tear Resistance and Biocompatibility of Polyurethane-Urea Elastomers for Artificial Heart Valves via Hydrogen Bonding Design.

ACS applied bio materials·2026
Same author

Mentorship as a Mechanism for Equity, Retention & Scientific Innovation in Neuroscience-related Careers.

Oxford open neuroscience·2026
Same author

Geometry and dynamics of annealed optimization in the coherent Ising machine with hidden and planted solutions.

Physical review. E·2026
Same author

Intrinsic space-time couplings governing multi-scale cortical dynamics.

bioRxiv : the preprint server for biology·2026
Same author

Ultra-High Dielectric Acceptor Enables 21% Efficiency and Thickness-Insensitive Organic Solar Cells.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Interfacial Engineering of PEDOT:PSS with Weyl Semimetals NbAs and NbP for High-Performance Organic Solar Cells.

The journal of physical chemistry letters·2026

相关实验视频

Updated: Mar 14, 2026

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

6.1K

神经网络计算的因果解释与贡献分解

Joshua Brendan Melander, Zaki Alaoui, Shenghua Liu

    ArXiv
    |March 13, 2026
    PubMed
    概括

    我们开发了CODEC (Contribution Decomposition),一种通过分析隐藏的神经元如何驱动输出来理解神经网络的新方法. CODEC揭示了因果过程,并使网络行为能够更好地控制和解释.

    科学领域:

    • 人工智能的人工智能
    • 计算神经科学是一种神经科学.
    • 机器学习 机器学习

    背景情况:

    • 了解神经网络的内部运作对于解释和操纵至关重要.
    • 目前的方法通常集中在激活模式上,限制因果洞察力.
    • 分析隐藏的神经元如何直接影响输出是更深入理解的关键.

    研究的目的:

    • 介绍CODEC (贡献分解),一种用于分析神经网络行为的新方法.
    • 揭示神经网络内的因果过程,这些因果过程不仅仅是从激活分析中看出来的.
    • 提高人工神经网络的可解释性和可控制性.

    主要方法:

    • 使用稀疏的自编码器将网络行为分解为隐藏神经元贡献的稀疏动机.
    • 应用CODEC进行图像分类网络和脊椎动物视网膜神经活动模型的基准测试.
    • 专注于分析神经元对网络输出的直接贡献,而不仅仅是激活.

    主要成果:

    • 贡献增加了跨网络层的稀疏性和维度.
    • 对网络输出的积极和消极贡献逐渐脱节.
    • 通过CODEC,可以对网络输出进行因果操作,并对图像组件进行可解释的可视化.
    • 在视网膜模型中发现了内部神经元的组合作用,并确定了动态受体场的来源.

    更多相关视频

    Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
    11:18

    Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

    Published on: March 2, 2015

    10.9K
    Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment
    08:43

    Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment

    Published on: August 7, 2017

    8.5K

    相关实验视频

    Last Updated: Mar 14, 2026

    Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
    08:51

    Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

    Published on: November 1, 2019

    6.1K
    Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
    11:18

    Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

    Published on: March 2, 2015

    10.9K
    Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment
    08:43

    Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment

    Published on: August 7, 2017

    8.5K

    结论:

    • 编码提供了一个强大的框架,用于理解跨层次层次的非线性计算.
    • 贡献模式作为机械洞察人工神经网络的信息单位.
    • 该方法提供了更好的解释性和对中间网络层的控制.