Learning Parametrization with Implicit Neural Representations

Description

In the search for new physics at the Large Hadron Collider (LHC) it is necessary to accurately learn the representation of events that may be described in different ways (point clouds, graphs, grids). Different detector systems can lead to different optimal representations and no single approach is ideal for all detector systems. Conventional representations are usually discrete (point clouds, grids etc.). This project focuses on an alternative approach of parametrizing the representation in terms of a continuous function and approximating it with a neural network.

Duration

Total project length: 175/350 hours.

Task ideas

Expected results

Requirements

Mentors

Please DO NOT contact mentors directly by email. Instead, please email ml4-sci@cern.ch with Project Title and include your CV and test results. The mentors will then get in touch with you.

Corresponding Project

Participating Organizations