查看“机器学习与人工智能”的源代码

* artificial neural networks (ANN)
: 气体的冷却 deepCool, deepHeat, and deepMetal:  arXiv:1901.01264
: 对quench的机制进行排序 [https://arxiv.org/pdf/1601.01258.pdf]

* unsupervised Random Forest
:找到SDSS中最怪异的星系  [https://arxiv.org/abs/1611.07526]
: https://arxiv.org/abs/2007.08530

* 恒星形成历史 [https://arxiv.org/abs/1903.10457]
: 基于数值模拟的结果，监督学习 
: Convolutional Neural Networks(CNN)
: Extremely Randomised Trees

* 高斯过程回归 （Gaussian Process Regressor）
:Scikit-Learn machine learning package for [[Python]]
:arXiv1901.02877 1908.04318

==图像相关==
*merger
:REALSIM [https://ui.adsabs.harvard.edu/abs/2019MNRAS.490.5390B/abstract]

*Galaxy morphology network [https://arxiv.org/abs/2006.14639]

* Morpheus
:https://ui.adsabs.harvard.edu/abs/2020ApJS..248...20H/abstract

*贾鹏的方法
:https://arxiv.org/abs/2002.09211

*deblend 
:Residual Dense Neural network (RDN) [https://arxiv.org/abs/2109.09550]
:sextractor做deblend [https://github.com/esheldon/sxdes]
:weaklense中的deblend [https://github.com/LSSTDESC/WeakLensingDeblending]

*图像生成
: [http://arxiv.org/abs/2203.11956] StyleGAN 生成的图片真实度最高，生成的图片可以增加星系样本的多样性，使得网络更具有泛化能力。

==算法==
*降维：tSNE
*降维：MDS Multidimensional Scaling, [https://zhuanlan.zhihu.com/p/141434196]
* 贝叶斯方法中的Simulation-based inference (SBI; also known as “likelihood-free” inference)：基于神经元的正向建模 [http://arxiv.org/abs/2203.07391]

==软件包==
*[[rapids]] 
*[[scikit-learn]]
*astroML   [https://www.astroml.org/astroML-notebooks/]
*[[jax]]
*[[pytorch]]
*[[tensorflow]]

==教程==
*https://github.com/WillKoehrsen/Machine-Learning-Projects