Title: Integrating Machine Learning and Uncertainty Quantification in Neutrino Physics and Dark Matter Experiments

Abstract: Over the past decade, the integration of machine learning (ML) techniques have led to innovation in the field of (Astro)particle physics. Despite the success of ML methods in solving complex problems, they often fail to provide information about the reliability of their predictions. In this seminar, we will explore uncertainty quantification in classification and regression problems within neutrino and dark matter experiments. Additionally, we will discuss how incorporating Bayesian networks improves analysis in dark matter experiments compared to traditional methods.