The AISSAI center is pleased to sponsor a hacking week focusing on the use of ML techniques in astrophysics.
The AISSAI hackweek is offered back-to-back and in the context of the AstroInfo school, but participation in both events is decoupled.
Important dates
Pre-registration deadline: May 9, 2023
Deadline for submission of proposals: May 9, 2023
Acceptance notification date: mid-May 2023
Hackathon dates: July 3-7
Logistics
The AISSAI Hackathon is planned as an in-person event. It will take place in Fréjus, in the south of France, in early July (see location below).
The number of participants will be limited to 20, including juniors and seniors. Senior participants must submit a hackathon project when registering (see CFP below). The organizers will guarantee the registration of senior participants whose hackathon proposals have been accepted.
Confirmed participants will be offered full accommodation (all meals + single room) for the whole week.
Due to the very limited number of participants, we will ask accepted participants to confirm their attendance promptly so that all places can be filled and those on the waiting list can be informed in good time.
It is mandatory that all participants read and adhere to the hackathon code of conduct.
Inquiries about the hackathon can be addressed to
hackathonaissai@sciencesconf.org
Call for hack proposal
We invite senior participants (e.g. with a permanent position) to submit hack proposals at the crossroads of astrophysics and machine learning.
We welcome all kinds of projects, as long as they involve and engage several participants throughout the week on various tasks and lead to a publishable result.
Here is a non-exhaustive list of topics of interest:
Detecting anomalies and outliers, searching for rare signals with ML
Methods for improving model interpretability
Models informed by astrophysics, models preserving symmetries and equivariances.
Deep learning for accelerating numerical simulations
Successful applicants will work with local organizers to prepare the hackathon material (project presentation, open data, existing code, starting notebook, etc.). We will provide dedicated time on a GPU-equipped French supercomputer throughout the week to achieve these objectives, with the possibility of extending this time to progress the project later.
Knowledge of Machine Learning is preferred but not mandatory, as a local team will be available to work with participants.
Please submit your proposals on the registration form by May 9, 23:59 AOE (Anywhere on Earth).
Location
Village Vacances Igesa « Destremau »
1848 Route de Cannes
83600 Fréjus
France
