The Edge of Tomorrow: Real-time Artificial Intelligence for Science
ECE 595 Seminar Series
February 21, 2025
11:00 AM - 12:00 PM
The Edge of Tomorrow: Real-time Artificial Intelligence for Science
Presenter: Nhan Tran, Fermi National Accelerator Laboratory
Abstract: Pursuing answers to fundamental questions about our nature requires searches for the ultra-rare and very subtle and the inspection of nature at extremely fine spatial and temporal scales. Cutting-edge experiments are often confronted with massive amounts of very rich data on which Artificial Intelligence (AI) techniques provide powerful insights. To accelerate scientific discovery, enabling powerful AI algorithms across the data processing continuum, as close to sensor front-ends as possible, is becoming increasingly valuable. To deploy AI in these challenging scientific environments, we require robust and efficient learning and usable and accessible tool flows for optimized training and implementation across a broad range of scientific domains. This talk will introduce the motivations and requirements for real-time AI applications for physics and connections to broader science and industry applications, the development of modern techniques for deploying them into our experiments, and open research questions and challenges.
Speaker bio: Nhan Tran is a Wilson Fellow at Fermilab. He completed his undergraduate degree in physics from Princeton University in 2005 and received his PhD from Johns Hopkins University in 2011, working on the compact muon solenoid (CMS) experiment at the Large Hadron Collider (LHC). He continued his work on the CMS experiment as a postdoctoral researcher at Fermilab. Tran’s research focus is on using accelerator-based experiments to search for new phenomena. He made significant contributions to the discovery and characterization of the Higgs boson at the LHC. He has worked on techniques and tools at the LHC to broadly enhance the physics capability: advancing the deployment of jet substructure tools, developing novel pileup mitigation techniques, and establishing tools to employ and accelerate machine learning in trigger electronics and computing. He has been involved in original analyses at the LHC to search for light dijet resonances and explore Higgs couplings at high momentum. Tran is a recipient of the URA Tollestrup Award, the APS Henry Primakoff Award, and the DOE Early Career Award.
Faculty host: Enis Cetin
Date posted
Feb 19, 2025
Date updated
Mar 6, 2025