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
Nervous Tissue: Neuron Types01:19

Nervous Tissue: Neuron Types

2.5K
Neurons, the fundamental units of the nervous system, can be classified based on both their structural and functional characteristics.
Structurally, neurons are categorized into three main types: multipolar, bipolar, and unipolar (or pseudounipolar). Multipolar neurons, which are the most common type in the brain and spinal cord, as well as all motor neurons, possess multiple dendrites and a single axon.
Bipolar neurons, on the other hand, have one primary dendrite and one axon. They are...
2.5K

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

Rapid neuronal labeling and functional imaging in the developing mouse brain with AAV-PHP.eB.

Cell reports methods·2026
Same author

Serum magnesium is associated with osteoporosis risk in postmenopausal women: a retrospective study and risk-prediction model.

Frontiers in medicine·2026
Same author

Multi-omics reveals different signatures of obesity-prone and obesity-resistant mice.

iMetaOmics·2026
Same author

An antioxidant, injectable hydrogel with mitochondrial fusion effect promotes inflamed dental pulp repair via immunomodulation and reactive oxygen species scavenging.

Biomaterials·2026
Same author

Hyodeoxycholic Acid Suppresses High-Fat-Diet-Promoted MC38-Syngeneic Colorectal Tumor Growth via Bile Acid Remodeling and Microbiota Modulation.

Nutrients·2025
Same author

Lightweight Reparameterizable Integral Neural Networks for Mobile Applications.

IEEE transactions on neural networks and learning systems·2025

相关实验视频

Updated: Jun 6, 2025

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

470

可分离的完整神经网络.

Jinhua Lin1, Xin Li1, Lin Ma2

  • 1Department of Computer Application Technology, Changchun University of Technology, PR China.

Neural networks : the official journal of the International Neural Network Society
|November 30, 2024
PubMed
概括
此摘要是机器生成的。

本研究介绍了移动设备的可分离的综合神经网络 (SINNs),与现有的综合神经网络相比,它可以降低计算成本和参数数量,同时在图像识别任务上保持竞争性性能.

关键词:
卷积神经网络是一种卷积神经网络.深度学习是一种深度学习.综合神经网络是一个完整的神经网络.

更多相关视频

Studying the Integration of Adult-born Neurons
09:00

Studying the Integration of Adult-born Neurons

Published on: March 25, 2011

13.8K
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.3K

相关实验视频

Last Updated: Jun 6, 2025

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

470
Studying the Integration of Adult-born Neurons
09:00

Studying the Integration of Adult-born Neurons

Published on: March 25, 2011

13.8K
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.3K

科学领域:

  • 深度学习 (Deep Learning) 是一种深度学习.
  • 计算机视觉 计算机视觉
  • 神经网络架构 神经网络架构

背景情况:

  • 积分神经网络 (INN) 使用连续积分运算符,但难以表示移动应用程序中常见的可分离卷积.
  • 可分离的卷积对于资源有限的设备上高效的深度学习至关重要.

研究的目的:

  • 开发一种新的神经网络架构,能够以连续的方式表示可分离的卷积.
  • 创建适合移动设备的轻量级可分离的综合神经网络 (SINNs).

主要方法:

  • 提出了一个可分离的积分层,将深度和点积分运算符结合起来.
  • 根据经典的CNN架构设计了五种类型的可分离整体块 (SIB).
  • 在资源有限的移动设备上构建和部署SINNs.

主要成果:

  • 在ImageNet数据集上,SINN的表现与最先进的INN的表现相当.
  • 与INN相比,计算成本降低了1/1.79倍.
  • 使用ResNet101骨干的SINN的参数比INN的参数少1.74倍.

结论:

  • 实际上,SINN在连续框架中有效地表示可分离的卷积.
  • 拟议的架构为移动深度学习提供了令人信服的性能和计算效率平衡.
  • SINNs继承了INN的结构修剪优势和可分离卷曲的效率.