Data Science Seminar / COMPASS

When:  Mondays every week
Time:   4:00pm - 5:00pm
Where: Peyton Hall Room 140 or Lewis Library Vislab
Organizers: Peter Melchior (melchior[at]; Adrian Price-Whelan (adrn[at]; Christina Kreisch (ckreisch[at]; Lachlan Lancaster (lachlanl[at]

Every week we discuss data science methods and applications from papers, reviews, software releases, etc. We also have demos for useful/fancy methods by locals and visitors through the COMPASS program.

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 the organizers.

Date Location Speaker   Title
9/14/2018 140 Peter Melchior Introduction to PyTorch
9/24/2018 033 Elinor Medezinski Galaxy detection and identification using deep learning and data augmentation
10/1/2018 033 Peter Melchior The Unreasonable Effectiveness of Recurrent Neural Networks
10/8/2018 033 Peter Melchior Understanding LSTM Networks
10/15/2018 033 Lachlan Lancaster Deep neural networks to enable real-time multimessenger astrophysics
10/22/2018 Vislab Patrick Crumley Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
10/29/2018 --- --- fall recess: no meeting
11/5/2018 Vislab Dan Foreman-Mackey (CCA) Practical Hamiltonian Monte Carlo in Python for Astronomers
11/12/2018 Vislab Boris Leistedt (NYU) Forward, causal modeling of galaxy photometry: Hierarchical causal models ↔ machine learning
11/19/2018 Vislab John Wu (Rutgers) Using deep convolutional neural networks to predict galaxy metallicity from three-color images
11/26/2018 --- --- no meeting
12/3/2018 033 Remy Joseph Sparse regularisation for strong gravitational lensing
12/10/2018 Vislab Richard Galvez (NYU) Artificial Intelligence and Heliophysics
12/17/2018 --- --- winter break
01/14/2018 TBA TBA TBA