# Research notes

Scarlet2 – Thoughts for a major redesignAstronomical source modeling and separation, all new and shiny |

Bayesian inference three waysRunning MCMC, Hamiltonian MC, and simulation-based inference with a few lines of code |

Proximal matrix factorization in pytorchConstrained optimization with autograd |

Data Science in Astronomy: pyTorch introductionNeural networks without clutter |

Data Science in Astronomy: Neural networks 101The structure and power of shallow networks for regression and classification |

Data Science in Astronomy: Classification TheoryThe common ideas behind classification with Naive Bayes, LDA, QDA, logit, and SVM |

Data Science in Astronomy: ClusteringClustering of cluster galaxies with K-means, Mean-Shift, MST, and the Gap statistic |

Data Science in Astronomy: Introduction and scikit-learnAn overview of jargon, plus multi-band detection by clustering in color space |

The magic of proximal operatorsConstrained optimization made easy |

Gaussian mixture models for AstronomyAn intro for observational data analysis projects |

Map projections for wide-field surveysWhat cartography can teach us about survey visualization |

Four massive clusters from DES SV dataWe went out to test DECam, and got galaxy clusters and filaments |