ECE 598 ZZ

Subject offerings of new and developing areas of knowledge in electrical and computer engineering intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: May be repeated in the same or separate terms if topics vary.

This course covers state-of-the-art techniques in generative modeling, focusing on diffusion and flow matching models. Students will gain a thorough understanding of the theory and practical applications of these models for generating high-dimensional data. Key topics will include the basics of generative models, the mathematical principles behind diffusion and flow-based methods, and real-world applications. The course will also prioritize hands-on learning through coding assignments and reviews of current research literature. Prerequisites: Knowledge of machine learning, linear algebra, calculus, and probability, python programming. ECE 313, CS 446/ECE449 or instructor approval.