About
## Secondary Vertex Reconstruction with Maskformer The High-Luminosity Large Hadron Collider will generate data in a challenging high pile-up environment, making the reconstruction of secondary vertices, crucial for identifying heavy-flavor quarks and searching for new physics, extremely difficult. This project addresses this by developing an end-to-end machine learning pipeline using the MaskFormer architecture. The core contribution was creating a highly efficient data conversion module to transform `.root` physics data into the ML-friendly `.h5` format. Following this foundational step, the project involves training the model and analyzing its results to ensure physics-accurate predictions. Further enhancements will be explored through advanced techniques such as hyper-parameter tuning, pre-training strategies, and post-training optimizations to maximize the model's performance and scientific potential..
0:00:00 Slide 1
0:02:18 Slide 2
0:03:54 Slide 3
0:05:10 Slide 4
0:06:50 Slide 5
0:07:52 Slide 6
0:09:44 Slide 7
0:13:34 Slide 8
The talk
Credits and licence
- Institution
- CERN
- Department
- Summer Student Lecture Programme General
- Speaker
- Sittipon Kumda
- Year
- 2025
- Language
- English
- Source
- CERN
- Licence
- CERN, as CERN states it. CERN's terms
- Attribution
- © CERN. CERN provides its audiovisual media free of charge for educational and informational use, credited to CERN; this lecture is shown in CERN's own player.
- Who can watch
- CERN gives no rating. Invisible Network shows it to Teens profiles and older, judged from what the source says about it. How courses are placed