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

Neural Circuits01:25

Neural Circuits

2.6K
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...
2.6K
Neural Regulation01:37

Neural Regulation

43.1K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
43.1K
Isotonic and Isometric Muscle Contractions01:22

Isotonic and Isometric Muscle Contractions

6.6K
Two primary types of muscle contractions are isotonic and isometric, each serving unique functions and involving distinct mechanisms. Both isotonic and isometric contractions are integral to the body's complex system of movement and stability. Isotonic exercises contribute significantly to functional strength and movement, while isometric contractions are crucial for maintaining posture and joint stability.
Isotonic contractions
Isotonic contractions occur when a muscle changes length while...
6.6K
State Space Representation01:27

State Space Representation

523
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
523
Improving Translational Accuracy02:07

Improving Translational Accuracy

14.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
14.1K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.5K
3.5K

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

Distinct Patterns of Directed Brain Connectivity in Focused Attention, Open Monitoring, and Loving Kindness Meditation: An Electroencephalographic Granger Causality Study with Long-term Meditators.

Journal of cognitive neuroscience·2026
Same author

Sensor movement drives emergent attention and scalability in active neural cellular automata.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

A bio-inspired minimal model for non-stationary K-armed bandits.

Biological cybernetics·2026
Same author

Hexagons all the way down: grid cells as a conformal isometric map of space.

PLoS computational biology·2025
Same author

Multitask learning of a biophysically-detailed neuron model.

PLoS computational biology·2024
Same author

Topological structure of population activity in mouse visual cortex encodes densely sampled stimulus rotations.

iScience·2024

相关实验视频

Updated: Jan 14, 2026

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

10.8K

神经网络中的同度表示提高了稳定性,提高了稳定性.

Kosio Beshkov1, Jonas Verhellen2, Mikkel Elle Lepperød3

  • 1Department of Physics, University of Oslo, Oslo, Norway. kosio.neuro@gmail.com.

Scientific reports
|October 21, 2025
PubMed
概括

神经网络可以通过保留数据结构来更好地学习,从而产生更强大,更准确的AI. 本研究介绍了一种连续和等级表示的方法,改进了概括和防御对抗攻击的方法.

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:

  • 数据结构对于学习至关重要;神经网络表示应该反映输入数据距离.
  • 神经科学表明,概括和强度取决于连续的,可微分的神经表示.
  • 在对象识别中观察到等级表示,这意味着需要多分辨率数据处理.

研究的目的:

  • 训练神经网络,在类内保持尺度结构,以实现连续和同度表示.
  • 开发一个网络架构,使内部表示的层次操作.
  • 调查是否保留公制结构可以提高分类的准确性和稳定性.

主要方法:

  • 训练神经网络使用同度规范化术语来保持课内距离.
  • 实施一种新的网络架构,用于对层次表示控制.
  • 使用MNIST,CIFAR10和玩具数据集对分类任务的性能进行评估.

主要成果:

  • 拟议的同度规范化提高了对MNIST和CIFAR10.0的对抗性攻击的稳定性.
  • 学习的表示被证明在数据集中是异比的,除了在决策边界附近.
  • 对表示的层次操纵有助于准确和强大的推断.

更多相关视频

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

相关实验视频

Last Updated: Jan 14, 2026

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

10.8K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

结论:

  • 在神经表征中保留尺度和层次结构对AI性能有好处.
  • 开发的方法提高了稳定性和准确性,为人工智能开发提供了有前途的方向.
  • 连续和同度表示是真实数据利用和改进概括的关键.