Speaker
Description
Current applications of machine learning in astrophysics focus on teaching machines to perform domain-expert tasks accurately and efficiently across enormous datasets. While essential in the big data era, this approach is limited by our intuitions and expectations, and provides at most only answers to the ‘known unknowns’. We are developing new tools to enable scientific breakthroughs by discovering unbiased interpretable representations of complex data ranging from observational surveys to simulations. Our tools automatically learn low-dimensional representations of complex objects such as galaxies in multimodal data (e.g. images, spectra, datacubes, point clouds, etc.), and provide exploratory access to arbitrarily large datasets using a simple interactive graphical interface. Our comprehensive discovery framework uses the learned representations downstream for simulation-based inference and model-driven experiment design. It is designed to be interpretable and to work seamlessly across datasets regardless of their origin.
| Affiliation of the submitter | Heidelberg Institute for Theoretical Studies (HITS) |
|---|---|
| Attendance | in-person |
