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

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

1.8K
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
1.8K
Vision01:24

Vision

59.4K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
59.4K
Associative Learning01:27

Associative Learning

1.2K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
1.2K
Visual System01:26

Visual System

1.7K
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
1.7K

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

<i>LsToll</i> Gene Mediates Antibacterial Immunity and Developmental Regulation in <i>Loxostege sticticalis</i>.

Insects·2026
Same author

Long-Term Outcomes From a Decade of Donation After Circulatory Death Heart Transplantation in Australia.

JACC. Heart failure·2026
Same author

Rapid Determination of Several Biogenic Amines in Cold-Chain Fish Samples by Portable Ion Trap Mass Spectrometry with Nano-Electrospray Ionization.

Foods (Basel, Switzerland)·2026
Same author

Aerosol Inhalation of a Recombinant H7N9 Hemagglutinin Antigen Elicits Systemic and Mucosal Immune Responses in Mice.

Viruses·2026
Same author

Localized hybridization chain reaction on self-assembled DNA nanospheres overcomes the kinetics-stability-complexity trilemma in miRNA sensing.

Biosensors & bioelectronics·2026
Same author

Gastrointestinal dysfunction in patients with Mowat-Wilson syndrome is associated with feeding difficulties and altered plasma neurotransmitters.

Frontiers in pediatrics·2026

相关实验视频

Updated: Jan 16, 2026

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

2.3K

DTL:参数和记忆效率高的解视觉学习.

Minghao Fu, Ke Zhu, Zonghao Ding

    IEEE transactions on pattern analysis and machine intelligence
    |October 1, 2025
    PubMed
    概括

    分解转移学习 (DTL) 减少了大型模型的GPU内存和可训练参数. 这种参数效率转移学习方法可以提高下游任务的准确性,例如对象检测和语义细分.

    科学领域:

    • 人工智能的人工智能
    • 机器学习 机器学习
    • 计算机视觉 计算机视觉

    背景情况:

    • 精细调整大型预训练模型会产生相当大的计算成本.
    • 现有的参数效率转移学习 (PETL) 方法在训练期间由于参数纠而难以减少GPU内存占用量.
    • 对于大规模的人工智能模型来说,需要有效的记忆和准确的转移学习技术至关重要.

    研究的目的:

    • 引入解转移学习 (DTL) 以减少GPU内存使用量和可训练参数的大型模型微调.
    • 为有效的知识传输提出一个新的紧侧网 (CSN) 架构.
    • 为了证明DTL在效率和准确性方面优于现有的PETL方法.

    主要方法:

    • DTL使用轻量级的紧侧网 (CSN) 从骨干模型中解开可训练的参数.
    • CSN使用低级线性映射来提取和重新注入特定任务的信息.
    • 对于像对象检测和语义细分等复杂任务,DTL被扩展为稀疏的架构设计.

    主要成果:

    • 与现有的PETL方法相比,DTL显著降低了GPU内存的使用量和可训练参数的数量.
    • 拟议的CSN有效地促进了跨各种下游识别任务的知识转移.
    • 在基准数据集上,DTL实现了比目前的PETL方法更高的准确率.

    更多相关视频

    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
    07:12

    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

    Published on: April 11, 2025

    878
    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

    1.0K

    相关实验视频

    Last Updated: Jan 16, 2026

    Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
    07:11

    Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

    Published on: December 8, 2023

    2.3K
    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
    07:12

    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

    Published on: April 11, 2025

    878
    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

    1.0K

    结论:

    • 对于大型模型,DTL提供了一种更高效,更有效的学习转移方法.
    • 对于内存受限制的训练场景,CSN架构提供了一个可行的解决方案.
    • DTL代表了参数效率转移学习的重大进步,特别是在计算机视觉任务中.