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

Amplifying Signals via Enzymatic Cascade01:22

Amplifying Signals via Enzymatic Cascade

8.4K
When a ligand binds to a cell-surface receptor, the receptor's intracellular domain changes shape, which may either activate its enzyme function or allow its binding to other molecules. The initial signal is amplified by most signal transduction pathways. This means that a single ligand molecule can activate multiple molecules of a downstream target. Proteins that relay a signal are most commonly phosphorylated at one or more sites, activating or inactivating the protein. Kinases catalyze...
8.4K
Protein Networks02:26

Protein Networks

2.3K
2.3K

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

Lifestyle interventions and 24-hour movement behaviors in preschool children: a systematic review and meta-analysis.

Frontiers in public health·2026
Same author

Wuqinxi exercise for mind and balance: Enhancing cognition, fall prevention, and quality of life in older adults with mild cognitive impairment.

PloS one·2026
Same author

Smart sensors, smarter players: The role of real-time monitoring in football training.

PloS one·2025
Same author

Microgravity-induced wet chemical etching of borosilicate glass enhances the process rate.

Scientific reports·2025
Same author

Time-course effects of cognitively engaging physical activity on executive function and self-control in younger school-aged children: a randomized controlled trial.

Frontiers in psychology·2025
Same author

Effects of ball combination training program combined with cTBS intervention on motor disorder in children with autism spectrum disorder.

Scientific reports·2025

相关实验视频

Updated: Jun 21, 2025

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions
07:34

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

Published on: March 25, 2014

9.9K

利用尖端神经网络进行主题建模.

Marcin Białas1, Marcin Michał Mirończuk1, Jacek Mańdziuk2

  • 1National Information Processing Institute, al. Niepodległości 188b, 00-608, Warsaw, Poland.

Neural networks : the official journal of the International Neural Network Society
|July 7, 2024
PubMed
概括

尖端神经网络 (SNN) 通过学习单词模式,可以有效地执行主题建模 (TM). 一个新的突发主题模型 (STM) 展示了与未经监督的自然语言处理中的既定方法相比的竞争性性能.

关键词:
在STDP中,STDP是最重要的.尖的神经网络的神经网络.尖的主题模型.主题建模 主题建模没有监督的学习学习.

更多相关视频

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

543
Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments
05:19

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Published on: November 12, 2019

7.0K

相关实验视频

Last Updated: Jun 21, 2025

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions
07:34

A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

Published on: March 25, 2014

9.9K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

543
Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments
05:19

Using Neuron Spiking Activity to Trigger Closed-Loop Stimuli in Neurophysiological Experiments

Published on: November 12, 2019

7.0K

科学领域:

  • 人工智能的人工智能
  • 计算语言学 计算语言学
  • 神经科学是一个神经科学.

背景情况:

  • 主题建模 (TM) 识别大型文本集团中的潜在主题.
  • 传统的TM方法通常依赖于基于统计或嵌入的方法.
  • 尖端神经网络 (SNN) 为模式识别提供了一个生物灵感的替代方案.

研究的目的:

  • 研究SNN的有效性,特别是使用Hebbian学习,用于无监督主题建模.
  • 为文本分析引入一种新的尖端主题模型 (STM).
  • 根据已建立的TM算法对STM的性能进行评估.

主要方法:

  • 文本数据被转换为SNN输入的尖峰序列.
  • 一个单层SNN被训练使用尖峰时间依赖的可塑性.
  • 每个SNN神经元代表一个不同的话题,重量表示单词相关性.
  • STM的性能与隐藏的迪里克莱特分配 (LDA),比特尔主题模型 (BTM),嵌入主题模型 (ETM) 和BERTopic进行了基准测试.

主要成果:

  • 提出的尖端主题模型 (STM) 成功发现了高质量的主题.
  • 与经典的TM方法相比,STM在三个不同的数据集 (20Newsgroups,BBC新闻,AG新闻) 中表现出了竞争力的表现.
  • 这项研究验证了这样一个假设,即Hebbian学习的SNN可以专注于检测有意义的单词模式.

结论:

  • 在未经监督的自然语言处理任务 (如主题建模) 中,SNNs具有很大的应用潜力.
  • STM提供了一种新的,生物可信的方法来揭示文本中的主题结构.
  • 这项研究为在计算语言学和信息检索中探索SNN开辟了新的途径.