"Machine Learning (ML) techniques are emerging as a competitive tool for
analysing and extracting information from large volumes of complex
high-dimensional data. In the last few years, the High Energy Physics
community has adopted and customised a variety of ML techniques for
various steps of data analysis for e.g., trigger, event reconstruction,
particle identification, jet tagging, signal/background classification,
etc. ML is also emerging as an alternative approach to perform model
independent searches for new phenomenon at particle physics experiments.
In this talk, I will give a brief introduction to the recent advances in
ML relating to model independent searches for BSM. Thereafter I will
focus on my latest work where we have proposed a new semi-supervised
algorithm for anomaly detection called Anomaly Awareness (AA). I will
show how AA works by considering a well-known “Fat Jet” topology for
new physics searches. I will also discuss our work using ML to exploit
the kinematic information in VH channel where we parameterized the
effect of new physics in the SMEFT framework."
Per partecipare: gruppo Teams Università di Genova numero 1npbr0h
(se si possiede un account Teams Unige, si può accedere con il codice.
Se invece si possiede solo un account Teams INFN, scrivere a
simone.marzani@ge.infn.it per essere aggiunti come ospiti).
Simone Marzani