Data Science Seminar (140)

When:  Fridays every week
Time:   3:30pm - 5:00pm
Where: Grand Central Conference Room (Room 140), Peyton Hall
Organizers: Peter Melchior (melchior[at] and Adrian Price-Whelan (adrn[at]

Every week we discuss data science methods and applications from papers, reviews, software releases, etc. We emphasize when to use specific methods and when not. We also have demos for useful/fancy methods by locals and visitors.

This semester we base the seminar on part III of the book Statistics, Data Mining, and Machine Learning in Astronomy (aka "the yellow book").

The setting is informal. Material should be presented directly from the source or on the white board, demos should be hands-on. We collect links to documents, source code, tutorials, etc. for later perusal in this github repo.

If you would like to present at the data science seminar, please contact Peter or Adrian.

Date Speaker   Title  
2/09/2018 Peter Melchior Introduction and scikit-learn  
2/16/2018 Adrian Price-Whelan Non-parametric density estimation  
2/23/2018 Peter Melchior (Gaussian) Mixture models  
3/2/2018 no meeting ---  
3/9/2018 Adrian Price-Whelan Mixture model applications  
3/16/2018 Jim Bosch How not to do photometry  
3/23/2018 Peter Melchior Clustering  
3/30/2018 no meeting ---  
4/6/2018 Dan Foreman-Mackey (CCA) TensorFlow  
4/13/2018 Adrian Price-Whelan Classification: Part 1  
4/20/2018 Peter Melchior Classification: Part 2  
4/27/2018 Justin Alsing (CCA) Likelihood-free inference beyond ABC  
5/4/2018 Andy Goulding Decision Trees & Random Forests  
5/11/2018 Peter Melchior Shallow Learning: Neural Networks 101  
5/18/2018 Peter Melchior Interpreting Networks  
5/25/2018 no meeting ---  
6/1/2018 Francois Lanusse (CMU) From image processing to modeling astrophysical systematics: the potential of Deep Learning for modern surveys