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

1.1K
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...
1.1K

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

The internal representation of fractions: component, holistic or hybrid?

Frontiers in neuroscience·2026
Same author

A partially shared magnitude system: Common and specialized neural substrates underlying spatial, numerical, and temporal arithmetic.

NeuroImage·2026
Same author

A study of notation dependence in fraction magnitude processing using event related potentials.

Scientific reports·2025
Same author

Modeling macroscopic brain dynamics with brain-inspired computing architecture.

Nature communications·2025
Same author

A neurofunctional signature of affective arousal generalizes across valence domains and distinguishes subjective experience from autonomic reactivity.

Nature communications·2025
Same author

The development of numerical mapping in preschool children.

PloS one·2025

相关实验视频

Updated: Jun 15, 2025

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

10.3K

通过互补的杂交,适应时空神经网络通过互补的杂交.

Yujie Wu1,2,3, Bizhao Shi4,5, Zhong Zheng1

  • 1Center for Brain Inspired Computing Research (CBICR), Department of Precision Instrument, Tsinghua University, Beijing, China.

Nature communications
|August 27, 2024
PubMed
概括

研究人员通过合并循环神经网络 (RNN) 和尖端神经网络 (SNN) 来开发混合的时空神经网络. 这种统一模型增强了复杂的时空数据的自适应处理,优于单个网络类型的性能.

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

494
Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees
13:55

Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees

Published on: July 21, 2014

12.9K

相关实验视频

Last Updated: Jun 15, 2025

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

10.3K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

494
Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees
13:55

Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees

Published on: July 21, 2014

12.9K

科学领域:

  • 机器智能是机器的智能.
  • 神经形态计算是一种神经形态计算.
  • 人工神经网络的人工神经网络

背景情况:

  • 由于高空间尺寸和时间丰富,时空数据处理需要先进的模型.
  • 循环神经网络 (RNN) 和尖端神经网络 (SNN) 提供了不同的方法 (外部与内在动态),但具有不同的范式.
  • 跨越不同要求的适应性时空数据处理的统一框架是具有挑战性的.

研究的目的:

  • 提出一种结合RNN和SNN的新型混合时空神经网络.
  • 创建一个统一的建模框架,用于可变时空数据的自适应处理.
  • 为了提高性能指标,如准确性,稳定性和效率.

主要方法:

  • 通过整合RNN和SNN开发了混合的时空神经网络.
  • 采用统一的替代梯度学习框架.
  • 利用赫森意识的神经元选择方法来平衡神经元类型.

主要成果:

  • 混合模型通过调整RNN和SNN神经元的比率来证明卓越的适应能力.
  • 在基准指标上的准确性,稳定性和效率指标上取得了更好的表现.
  • 性能优于传统的单一范例RNN和SNN.
  • 在不同的环境中展示机器人任务的潜力.

结论:

  • 拟议的混合时空神经网络为处理各种时空数据提供了通用和有效的路线.
  • 这种统一的框架为现实应用提供了增强的适应能力.
  • 这种方法为更加多功能和高性能的人工智能系统铺平了道路.