End-to-End Deep Learning Reconstruction for CMS Experiment

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.

This project will focus on the integration of E2E code with the CMSSW inference engine for use in reconstruction algorithms in offline and high-level trigger systems of the CMS experiment.

Duration

Total project length: 175/350 hours.

Task ideas

Integration/interface of E2E with the CMSSW inference engine
Test and benchmarking of inference on GPUs

Expected results

Integrated code within CMSSW classes
Benchmark of end-to-end deep learning inference on cpu and gpu

Requirements

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

Mentors

Emanuele Usai (Brown University)
Davide DiCroce (University of Alabama)
Shravan Chaudhari (New York University)
Sergei Gleyzer (University of Alabama)
Michael Andrews (Carnegie Mellon University)

Please DO NOT contact mentors directly by email. Questions should instead be directed to ml4-sci@cern.ch which is forwarded to mentors. To submit your proposal, CV, and test task solutions, please use this Google form.