A3D3 Seminar: Josh Bloom

Monday 13 May 2024, 12:00 → 13:00 US/Pacific

Title: The Real AI Revolution in Astronomy Hasn't Happened Yet

 

Abstract: As a data deluge swamped traditional approaches, Astronomy, by necessity began to leverage AI/ML methods to facilitate discovery and inference at scale. Despite ongoing successes in the midstream (just after data is collected), I argue that our field sits just at the beginning of the real revolution where AI/ML becomes integrated and integral to the entire scientific workflow. From telescope and instrument design, to real-time control, to survey optimization, there is tremendous potential for AI/ML to improve the upstream efficiencies of data collection.  Likewise, downstream from data are exciting opportunities for AI-enabled hypothesis generation and human-centered exploration. I will ground this talk with specific examples of ongoing work in simulation based inference, self-supervised ML, foundation models, neural compression, and reinforcement learning.

 

 

Bio: Joshua Bloom is a Miller Professor at the University of California, Berkeley. He teaches radiative processes, high-energy astrophysics, and a graduate-level "Python for Data Science" course. He has published over 300 refereed articles on time-domain transients events, machine learning, and telescope/insight automation. Bloom co-founded the Berkeley Institute for Data Science. He has been awarded the Data-Driven Discovery prize from the Gordon and Betty Moore Foundation and the Pierce Prize from the American Astronomical Society; he is also a former Sloan Fellow, Junior Fellow at the Harvard Society, and Hertz Foundation Fellow. He holds a PhD from Caltech and degrees from Harvard College and Cambridge University. He was co-founder and CTO of Wise.io, an AI application startup, acquired by GE Digital in 2016. His book on gamma-ray bursts, a technical introduction for physical scientists, was published by Princeton University Press.

 

The A3D3 Seminar is a monthly lecture series that hosts scholars working across applied areas of artificial intelligence, such as hardware algorithm co-development, high energy physics, multi-messenger astrophysics,  and neuroscience. Our presenters come from all four domain fields and include occasional external speakers beyond the A3D3 science areas, governmental agencies and industry. The seminar will be recorded and published in YouTube. To receive future event updates, subscribe here.