University of Cambridge > Talks.cam > HEP phenomenology joint Cavendish-DAMTP seminar > Miguel Crispim Romao - Artificial Intelligence and Machine Learning for Collider and Beyond the Standard Model Physics

Miguel Crispim Romao - Artificial Intelligence and Machine Learning for Collider and Beyond the Standard Model Physics

Add to your list(s) Download to your calendar using vCal

  • UserMiguel Crispim Romao (Southampton U. and LIP, Minho)
  • ClockFriday 03 February 2023, 16:00-17:00
  • HousePotter Room (B1.19).

If you have a question about this talk, please contact Maeve Madigan.

In recent years, High Energy Physics (HEP) has seen a resurged interest in Artificial Intelligence and Machine Learning (AI/ML), driven by the current renaissance of these fields. Whilst most of the AI/ML applications in HEP have been developed in an experimental context, there is a wealth of unexplored ideas for the application of AI/ML to phenomenological and theoretical studies.

In this talk, I will discuss some of our recent work on applying AI/ML to Collider and Beyond the Standard Model (BSM) Physics. For the Collider applications, I will focus on the efforts to isolate jets that have interacted with the Quark-Gluon Plasma, an essential task to enable using jets as a probe for medium properties. I will then discuss the application of AI/ML algorithms for BSM model building, with a particular focus on black box search algorithms to find valid multidimensional parameter space regions of highly constrained models, where random sampling efficiency can be prohibitively low.

This talk is part of the HEP phenomenology joint Cavendish-DAMTP seminar series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity