Machine Learning for Physical Sciences and Systems

Catalog description

Foundational knowledge in applied aspects of machine learning, including methods for handling small, noisy, and imbalanced data; feature selection and representation learning; model selection and assessment; interpretable machine learning; and uncertainty quantification. Students will also gain exposure to state-of-the-art research in scientific machine learning, including applications to data-driven learning of dynamical systems and self-driving labs. Topics will be discussed in the context of recent advances in machine learning for materials, chemistry, and physics applications, with an emphasis on unique opportunities and challenges at the intersection of machine learning and science.