Anomaly detection has become a popular, complementary approach in the search for new physics at the LHC, aiming to identify rare or unexpected events within vast datasets. This seminar will present recent advances in anomaly detection at CMS, showcasing both offline analysis results and an innovative trigger strategy that leverages machine learning to enhance real-time detection of potential signals beyond the Standard Model. By enabling dynamic, data-driven response to rare processes, this approach pushes the boundaries of discovery, as demonstrated by recent CMS findings.
Bio: Dr. Jennifer Ngadiuba is an Associate Scientist and Wilson Fellow at Fermi National Accelerator Laboratory, specializing in the application of artificial intelligence to particle physics. Her innovative research focuses on real-time data analysis techniques and model-agnostic searches for physics beyond the Standard Model at the Large Hadron Collider's CMS experiment. Ngadiuba's contributions have earned her several accolades, including the 2024 IUPAP C11 Early Career Scientist Prize and the U.S. Department of Energy's AI4HEP award. With a background from institutions like CERN and Caltech, she is at the forefront of integrating AI technologies into particle physics, enhancing data processing and analysis capabilities for future discoveries.