.png){kind=icon}
返回
Solving inverse problems using normalizing flow prior: Application to optical spectra
.png){kind=icon}
PRE
AI
DOI：10.1103/PhysRevB.109.165130.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We introduce a machine learning approach for solving ill-posed inverse problems, specifically addressing the Fredholm integral equation of the first kind. Harnessing the powerful capabilities of normalizing flows to approximate data distributions, combined with a robust probabilistic framework, our approach stands out by delivering robust solutions capable of handling high-level noises and out-of-distribution data and providing uncertainty estimation. A distinct feature lies in the unsupervised learning framework inherent in deep generative models, providing our approach with unparalleled flexibility across diverse experimental setups. This flexibility is exemplified through the successful application of our method to measured optical spectra.
Keyword:
DENSITY-ESTIMATION
INFERENCE
期刊
IF:
3.7
论文数:
15.4W
被引数:
41.0W
机构
引用论文
Incentive Based Multi-Objective Optimization in Electric Vehicle Navigation including Battery Charging含电池充电的电动汽车导航中基于激励的多目标优化
OAAI
OAAI分享收藏Electron-boson spectral density functions of cuprates obtained from optical spectra via machine learning.png)
PHYSICAL REVIEW B
OAAI
PHYSICAL REVIEW BIF3.7
OAAI分享收藏
查看更多内容