The Freedom Trail of Code: Boston AstroML Hackathon
Embark on a revolutionary adventure at The Freedom Trail of Code to hack problems in astrophysics with machine learning, organized by the NSF Institute for Artificial Intelligence and Fundamental Interactions (IAIFI).

Taking place in the Boston area between the 22nd and 24th of January, 2024. Participants will team up to tackle real-world astrophysical problems leveraging machine learning. We welcome both less experienced participants and machine learning gurus looking for interesting problems to solve with AI. We promise all an exciting week of caffeine-fueled coding sessions. Lunch will be provided.

Organizers
Riccardo Arcodia (rarcodia@mit.edu)
Dillon Brout (dbrout@bu.edu)
Carolina Cuesta-Lazaro (cuestalz@mit.edu)
Alex Gagliano (gaglian2@mit.edu)
Siddharth Mishra-Sharma (smsharma@mit.edu)
Daniel Muthukrishna (danmuth@mit.edu)

To make the most out of the hack, we recommend those less with machine learning to review the awesome UvA Deep Learning tutorials in this link:
  • Firstly, familiarize yourself with the most popular machine learning libraries in python: PyTorch (tutorial link) and Jax (tutorial link). If you have never worked on ML, PyTorch might have a kinder learning curve, although Jax can be extremely useful and fast for scientific problems. Check this out to transition from PyTorch to Jax.
  • Follow Tutorials 3 and 4 for an overview of training machine learning models in either of the frameworks.
  • If you are interested in the "Generative everything" hack project, follow the deep auto encoders and normalizing flows tutorials.
  • For "simulation-based everything" check out this tutorial.

Collections of papers on Astro x ML
If you are looking for inspiration on interesting projects at the intersection of machine learning and astrophysics check out these resources: 
Sign in to Google to save your progress. Learn more
Name *
E-mail *
Affiliation(s) *
Career level *
What are your research interests? Please provide a brief description (~1 sentence)
What is your familiarity with machine learning? *
What project(s) would you be interested in joining? Please select your top three choices
First choice
Second choice
Third choice
Generative everything: Understand the generative model paradigm, and learn how to train diffusion generative models for a dataset of your choosing. Explore their utility for emulation, likelihood evaluation, posterior estimation, and anomaly detection.
Simulation-based everything: Build up the tools necessary to do simulation-based (or likelihood-free) inference. If you have a forward model or simulator for your data and are sick of losing information by using summary statistics, this may be for you!
Multimodal everything: Understand how to train joint embeddings across or within modalities. Examples: (1) images + spectra + light curves, or (2) the same object observed by different instruments. Explore the structure of joint embeddings and how to use them for various downstream tasks. Bring your own multi-modal datasets!
Anomaly detection: Extract informative features and build lower-dimensional representations of your dataset to find the rarest and strangest instances! We'll hack models for zero-shot and few-shot learning.
Super resolution everything: Enhancing the resolution of simulations that are too expensive to run at high resolution, for example hydrodynamical simulations of galaxy formation.
Clear selection
Bring your own data/problem! 

Do you have an interesting dataset that could be used in the projects described above? 

Do you have other interesting problems in mind that you think would be suitable for the hackathon? 

We'd love to hear about them and help you turn them into a hack project.
Would you be interested in leading a short (<1 hour) breakout discussion? If so, on what topic?
What would you hope to get out of the hackathon?
Dietary restrictions
Anything else you'd like to ask or comment on?
Submit
Clear form
Never submit passwords through Google Forms.
This content is neither created nor endorsed by Google. - Terms of Service - Privacy Policy

Does this form look suspicious? Report

Google Forms