Difference between revisions of "TDIS GNN Tracking"
From Hall A Wiki
(→Articles and resources) |
m |
||
| Line 21: | Line 21: | ||
[https://github.com/gnn-tracking GitHub page on GNN tracking with some code] | [https://github.com/gnn-tracking GitHub page on GNN tracking with some code] | ||
| − | ==Other Tracking Info | + | ==Other Tracking Info== |
[https://doi.org/10.48550/arXiv.1806.05880 Interfacing Geant4, Garfield++ and Degrad for the Simulation of Gaseous Detectors] | [https://doi.org/10.48550/arXiv.1806.05880 Interfacing Geant4, Garfield++ and Degrad for the Simulation of Gaseous Detectors] | ||
Revision as of 16:01, 3 August 2023
Graph Neural Networks (GNN) are a type of machine learning. GNN algorithms are being increasingly used for track finding and could be the best method of tracking for the mTPC.
Articles and resources
Graph Neural Networks for Particle Tracking and Reconstruction
Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
Charged Particle Tracking via Edge‐Classifying Interaction Networks
Belle 2 GNN Tracking
Belle2 GNN Poster at CHEP 2023. (See link to poster at bottom of page.)
GNN-based Track and Vertex Finding
Full Event Interpretation using Graph Neural Networks - Lea Reuter Master's Thesis
GitHub page on GNN tracking with some code
Other Tracking Info
Interfacing Geant4, Garfield++ and Degrad for the Simulation of Gaseous Detectors
