Séminaires, soutenances
Search for new physics with the ATLAS experiment using unsupervised Machine Learning
par
→
Europe/Paris
9109 (Salle)
9109
Salle
Description
The Standard Model of particle physics is one of the most validated theories available. However, we know that it is still incomplete. In order to find new physics Beyond the Standard Model, experiments like ATLAS have been collecting a huge amount of high energy collision data. Analyzing this complex dataset requires to develop analysis strategies based on advanced techniques like Machine Learning. In this presentation, we will explore an alternative analysis strategy based on unsupervised MachineLearning and model independent techniques. The objective is to find new physics without relying on heavy simulations and on signal hypotheses. We will define all the tools needed to build such a strategy and test them on the benchmark open dataset provided by the LHC Olympics 2020 challenge.
