Gregor Kasieczka

"Deep & Heavy: Using machine learning for boosted resonance tagging"


Abstract:
Deep learning is a recent development in computer science, based on creating 
computational models that feature multiple layers and correspondingly increasingly 
higher levels of abstraction. We use the problem of distinguishing hadronic top quark 
decays from light quark and gluon jets (top tagging) as a starting point for a tour of 
deep learning techniques in particle physics.