In this course students will be exposed to the applications of machine learning for materials design, including physical metallurgy, catalysis and mechanics of materials. We will begin by conducting a review of statistical and numerical methods, and programming in R and Python. Then, the most important machine learning techniques of relevance to materials science will be described. This will include linear, nonlinear and logistic regression, decision trees, artificial neural networks, deep learning, supervised and unsupervised learning. Thereafter, the students will be provided hands-on experience on analyzing data and apply ML approaches through a set of case studies, pertaining to alloy design, additive manufacturing, and catalyst design. Finally, students will apply these skills through a term project on materials science problem of their interest.

This course has been selected for Data Analytics emphasis in FASE at the graduate level. Due to the broad nature of course topics, we encourage students from Chem Eng, MIE, Chemistry, and other departments.