Machine Learning in Astronomy: Possibilities and Pitfalls

This symposium is under the broad umbrella of astroinformatics and astrostatistics but with an emphasis on the dissemination and demystification of deep learning techniques. We hope to encourage fusion of large datasets to enable exploration of combined parameter spaces that have so far remained unexplored. Using such diverse types as images, time series, spectra, and astrophysical simulations, one of our aims is to establish a list of reproducible "best-practices" solutions for astronomy data.

The symposium will also have sessions on more traditional machine learning, such as random forests, especially elucidating areas where deep learning is an overkill (and also sometimes ill-advised). We will supplement this with other astroinformatics sessions including those on methodology transfer to and from other science (e.g. Earth science, medical sciences etc.), visualization, simulations, astrostatistics and so on.

This conference also doubles as the 12th in the annual series of Astroinformatics conferences, sharing the core philosophy and many of the topics.

As things stand the symposium will be in-person and part of the IAU Genereal Assembly in Busan. We will keep an eye on the evolving situation wrt the pandemic and abide by the decisions the IAU makes. As per the current norms only up to 20% speakers are allowed to be remote. All attendees, in-person or remote, have to register. See the registration page for important dates.