Machine Learning in Materials Design

Catalog description

This course introduces the ideas of experimental design and decision making under uncertainty, guided by principles of statistical learning. By the end of the course, you should be able to: articulate principles of experimental design; execute methods of Bayesian optimization; quantify uncertainty in experiments and develop methods for propagating uncertainty from inputs to outputs. Along the way, students will learn about ANOVA, MCMC, and Kalman filters, among other techniques. Exercises and examples will be drawn from chemical, physics, and materials datasets.