Physics in Machine Learning Workshop

BIDS Research Project


May 29, 2019
8:15am to 7:30pm
190 Doe Library
Get Directions


This workshop focused on substantive connections between machine learning (including but not limited to deep learning) and physics (including astrophysics). Namely, we are interested in topics like imbuing physical laws into training (e.g., physics regularization of layers), learning new physical phenomena from learned models, physics-constrained reinforcement learning, prediction outside training parameters, causal inference, and the (physical) interpretability of models. Registration has closed for this event.


Links to individual talks/abstracts are also included in the agenda below.

8:15-8:30   Arrival and Registration
8:35-8:40   Logistics & Introduction -- Josh Bloom, UC Berkeley Astronomy
8:40-8:50   Welcome and Introductory Remarks  -- UC Berkeley Provost Paul Alivisatos, Chemistry

Producing & Discovering Dynamical Models -- Moderator, Laura Waller

Incorporating Physics directly into the Models -- Moderator, Fernando Pérez

Generative Models -- Moderator, Eric Jonas

Learning with Physical Systems -- Moderator, Federica Bianco

Code of Conduct

Scientific Organizing Committee
Joshua Bloom (UC Berkeley)
Laura Waller (UC Berkeley)
Fernando Perez (UC Berkeley)
David Hogg (NYU)
Kyle Cramner (NYU)
Benjamin Nachman (LBNL)

Local Organizing Committee
Stacey Dorton
Stefan van der Walt
Francois Lanusse
Peter Nugent

If you have any questions, please contact or Josh Bloom.


Joshua Bloom

Professor, Department of Astronomy

Josh Bloom an astronomy professor at the University of California, Berkeley, where he teaches high-energy astrophysicsPython bootcamps, and a graduate-level class on Python for data-driven science. He has published more than 250 refereed articles, largely on time-domain transients events and telescope/insight automation. Expressed in his research is output of a collaborative effort between talented astronomers, statisticians, and computer scientists (ranging from students to peers) at the nexus of physics, scalable computation, and machine learning.  His book on gamma-ray bursts was published in 2011, as part of the "Frontiers in Physics" series by Princeton University Press. He has been awarded the Pierce Prize from the American Astronomical Society, and he is a former Sloan Fellow, Junior Fellow at the Harvard Society, and Hertz Foundation Fellow. He holds a PhD from Caltech and degrees from Harvard and Cambridge University. Recently, he has working as co-PI of the Moore-Sloan Data Science Initiative at UC Berkeley and an elected member of the management oversight body of the Large Synoptic Survey Telescope (LSST).