Winter 2026

No description currently available. 

Once the quarter starts, instructor approval is required to maintain enrollment in the course, including if students do not have the listed pre-requisite courses completed.

No description currently available.

Once the quarter starts, instructor approval is required to maintain enrollment in the course, including if students do not have the listed pre-requisite courses completed.

Interactive AI systems are evolving beyond traditional mobile and web interfaces into new form factors such as extended reality glasses and collaborative robots, expanding AI’s potential to assist users in real-life tasks (e.g., sports training, cooking, vehicle repair). These developments also introduce challenges in interface design for safety and correct execution, effective instruction and feedback, preservation of human agency, ethics, and explainability.

Machine learning on graphs has emerged as an important research topic that finds applications in many domains including social networks, drug discovery, brain networks, and other sciences. This course will discuss recent advances in machine learning on graphs including neural network architectures and methods to encode graphs into low-dimensional spaces to facilitate machine learning. Specific topics include neural architectures, representations, explainability, and symmetry.

This graduate course gives an overview of machine learning for planning and control of complex dynamical systems. The central topic is the mathematical foundations of reinforcement learning in continuous state and action spaces. Supplementary topics include data-driven dynamics models, imitation learning, and robustness/adaptivity to environment shifts. Students will develop a thorough understanding of fundamental algorithms and learn to select appropriate methods based on the problem's interaction and information protocols.

This course explores fundamental tools for analyzing and designing trustworthy machine learning systems through the lens of information theory, statistics, and learning theory. We study reliability guarantees for modern models by quantifying generalization, fairness, and privacy. We will also introduce practical aspects of watermarking and IP protection for large generative models.