Machine Learning for Chemical and Dynamical Data

Catalog description

Introduction to machine learning methodologies for the chemical sciences, with an emphasis on the current state-of-the-art for applications to both experimental and computational data. The course will be hands-on and final projects will be a major component of the coursework. Material covered will include neural networks, classification and regression, image analysis, graph neural networks, learning potential energy surfaces, coarse-graining, Monte Carlo simulation, and applications to quantum chemistry and molecular dynamics. Prerequisite: knowledge of undergraduate level quantum mechanics and statistical mechanics at the levels of Chem 173 and Chem 175. Experience with Python highly recommended.