بعد أكاديمية كاوست
As of October 2026, Dimah is an undergraduate student at King Saud University. Dimah completed the KAUST Academy AI Specialization in September 2026 after an AI internship at CERN with the CMS experiment, and presented a poster on sheaf neural networks for particle detectors.
المشروع الصيفي
تخصص الذكاء الاصطناعي · دفعة 2026
SHEAF Neural networks for Pattern Recognition in Particle Detectors
Modern particle detectors generate enormous amounts of high-dimensional data by recording the energy deposited by particles traversing the detector. A fundamental chal- lenge is identifying which detector signals originate from the same particle, particularly in the high-density collision environment expected at the High-Luminosity Large Hadron Collider (HL-LHC). This problem can be formulated as a graph-based pattern recognition task, where reconstructed detector objects are linked to recover complete particle showers. This project investigates the use of Sheaf Neural Networks (SNNs) for the Trackster Linking task in the CMS High-Granularity Calorimeter (HGCAL). By replacing uniform graph message passing with learned edge-specific transformations, SNNs provide a more flexible mechanism for information exchange between neighboring Tracksters, particularly in heterophilic graph regions. The proposed model was evaluated against a baseline Graph Neural Network under identical training conditions and demonstrated improved class separation while maintaining strong edge classification performance, highlighting the potential of sheaf-based message passing for particle reconstruction.
مع أكاديمية كاوست
- دفعة 2026
المنظمة الأوروبية للأبحاث النووية (CERN) · التدريب الصيفي في الذكاء الاصطناعي
هل تريد تحديث بياناتك أو حذفها؟ تواصل معنا.