Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Difference from Background: Limit of Detection

Difference from Background: Limit of Detection

The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...

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

Single-pixel imaging for edge images using deep neural networks.

Applied optics·2022

Same author

Real-time single-pixel imaging using a system on a chip field-programmable gate array.

Scientific reports·2022

Same author

Single-path single-shot phase-shifting digital holographic microscopy without a laser light source.

Optics express·2022

Same author

Real-valued diffraction calculations for computational holography [Invited].

Applied optics·2022

Same author

Roadmap on Recent Progress in FINCH Technology.

Journal of imaging·2021

Same author

Mitigating ringing artifacts in diffraction calculations using average subtractions.

Applied optics·2021

Search research articles

相关实验视频

Updated: May 30, 2026

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

使用体积全息光学元素的波面偏差耐受的衍射深度神经网络.

Ikuo Hoshi¹, Koki Wakunami², Yasuyuki Ichihashi²

¹Applied Electromagnetic Research Center, National Institute of Information and Communications Technology, Nukui-Kitamachi, Koganei, Tokyo, 184-8795, Japan. hoshi@nict.go.jp.

Scientific reports

|January 8, 2025

概括

本研究引入了使用体积全息光学元件 (vHOE) 的衍射深度神经网络 (D2NN) 的新训练方法. 该方法成功地弥补了未知的波浪偏差,显著提高了光学实验中的AI计算精度.

关键词:

适应光学适应光学衍射深度神经网络衍射深度神经网络一个全息光学元件.机器学习是机器学习.

更多相关视频

Compact Lens-less Digital Holographic Microscope for MEMS Inspection and Characterization

Compact Lens-less Digital Holographic Microscope for MEMS Inspection and Characterization

Published on: July 5, 2016

Lens-free Video Microscopy for the Dynamic and Quantitative Analysis of Adherent Cell Culture

Lens-free Video Microscopy for the Dynamic and Quantitative Analysis of Adherent Cell Culture

Published on: February 23, 2018

相关实验视频

Last Updated: May 30, 2026

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

Compact Lens-less Digital Holographic Microscope for MEMS Inspection and Characterization

Compact Lens-less Digital Holographic Microscope for MEMS Inspection and Characterization

Published on: July 5, 2016

Lens-free Video Microscopy for the Dynamic and Quantitative Analysis of Adherent Cell Culture

Lens-free Video Microscopy for the Dynamic and Quantitative Analysis of Adherent Cell Culture

Published on: February 23, 2018

科学领域:

光学和光子学在光学和光子学.
人工智能的人工智能
计算科学计算科学

背景情况:

人工智能计算性能需求的增加推动了对新型计算架构的研究.
衍射深度神经网络 (D2NN) 通过衍射光学元件 (DOE) 使用光学调制提供高速AI计算.
体积全息光学元件 (vHOE) 提供独特的波长和角度选择性,但容易产生制造错误,导致波面偏差.

研究的目的:

开发和演示D2NN的培训方法,可以适应未知的波面偏差.
用拟议的适应性培训方法评估使用vHOE的D2NN的性能.
探索基于vHOE的D2NN在先进光学计算应用中的潜力.

主要方法:

提出了一种新的培训方法,使D2NN能够适应未知的波面偏差.
在D2NN架构中制造并集成体积全息光学元件 (vHOE).
进行了手写数字分类的光学实验,以验证拟议的方法.

主要成果:

适应训练方法在光学实验中显著提高了分类准确度,大约提高了58个百分点.
使用vHOE展示了一个功能性的D2NN,能够处理复杂的光学偏差.
在现实世界的光学实验环境中验证了拟议方法的有效性.

结论:

开发的培训方法有效地弥补了基于vHOE的D2NNs中的波面偏差.
这项研究为更强大,更准确的光学AI计算系统铺平了道路.
这些发现表明,在多波长并行光学计算,生物成像和光通信方面有前途的应用.