Equivariant Neural Networks to explore the underlying symmetries in particle physics events

Description

One of the important aspects of searches for new physics at the Large Hadron Collider (LHC) involves the identification and reconstruction of single particles, jets and event topologies of interest in collision events. The End-to-End Deep Learning (E2E) project in the CMS experiment focuses on the development of these reconstruction and identification tasks with innovative deep learning approaches.

Task ideas

Develop suitable equivariant neural network models and use them to analyze the collision data
Benchmark the equivariant neural network with vision transformers and convolution-based models
Extend the idea of Equivariant Neural Networks to exploit symmetries to finding and understanding symmetries and asymmetries in the data

Expected results

Achieve competitive results using equivariant neural networks
Benchmark the models with other previous works in terms of speed, performance and data efficiency.

Requirements

C++, Python, PyTorch, Tensorflow and some previous experience in Machine Learning.

Task

Please use this link to access the test for this project. Tests will be published by Feb. 24

Mentors

Emanuele Usai (Brown University)
Ruchi Chudasama (University of Alabama)
Shravan Chaudhari (BITS Pilani Goa)
Sergei Gleyzer (University of Alabama)

Please DO NOT contact mentors directly by email, and instead please send project inquiries to ml4-sci@cern.ch with Project Title in the subject and relevant mentors will get in touch with you.