Graph Transformers for Fast Detector Simulation

Description

DeepFalcon is an ultra-fast non-parametric detector simulation package that automatically abstracts detector response, usually done by hand in fast-simulators used by particle physics experiments. The goal of this project is to extend the existing Graph Variational Autoencoder model in DeepFalcon with a transformer model to improve end-to-end simulation of the detector deposits.

Task ideas and expected results

Duration

Total project length: 175 hours.

Requirements

Strong machine learning skills, good knowledge of C++ and Python. Interest in Machine Learning algorithms and applications.

Mentors

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.

Corresponding Project

Participating Organizations