Pushing the boundaries of neutrino physics with deep learning
by
48/2-224 - Madrone
SLAC
Deep learning is playing an increasingly important role in particle physics, offering powerful tools to tackle complex challenges in data analysis. This seminar presents a range of advanced deep-learning techniques applied to neutrino physics, with a particular focus on the T2K experiment. The discussion includes the use of cutting-edge models such as transformers, domain adaptation strategies like contrastive learning, and anomaly detection methods. These methods address key challenges in data analysis, enabling better classification and more precise reconstruction. Their integration boosts pipeline performance and supports deeper scientific insights. Additionally, I will briefly comment on applications outside particle physics, specifically in the context of identifying tumours from CT scans, where similar deep-learning strategies are being adapted to aid medical diagnostics.
Zoom: https://stanford.zoom.us/j/98973156241?pwd=cEU5RFdlVXoyc0JTeTlDMkozKzQ5UT09