Speaker
Dr
Saul Alonso Monsalve
(ETH Zurich)
Description
Deep learning is becoming an increasingly important part of particle physics, providing powerful ways to meet the growing demands of modern data analysis. This talk highlights a selection of advanced deep-learning approaches developed for neutrino physics. I will discuss recent progress using models such as transformers, along with domain-adaptation techniques including contrastive learning, and approaches to anomaly detection. Together, these methods help address persistent challenges in tasks such as event reconstruction, improving both accuracy and robustness. By integrating them into the analysis chain, we can enhance overall pipeline performance and, ultimately, extract richer scientific insight from the data.
