Delving into the cutting- edge field of AI-driven materials discovery, equipping students with the tools to develop advanced algorithms that can autonomously learn from data, make predictions, and direct future experiments.

Students will explore how AI models such as decision trees, Bayesian optimization, and other statistical methods can be combined with adaptive strategies to propose new experiments and calculations in an iterative loop. Building on the foundations from MSE 465, with a hands-on emphasis on the design and implementation of AI workflows. Students will practice balancing exploration and exploitation strategies, as well as design their own. Culminating in a final project where students will deploy their workflows to control a self-driving lab, guiding an autonomous materials optimization campaign.