This course provides an in-depth exploration of the mathematical concepts and algorithms underlying generative models in artificial intelligence. Students will learn about the theoretical basis of various generative techniques such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and other probabilistic models. The course emphasizes the development of a strong mathematical understanding to analyze and improve generative models, with applications ranging from image and video generation to complex problem-solving in unsupervised learning environments.
Course Prerequisite(s)
625.603 Statistical Methods and Data Analysis, multivariate calculus, and basic knowledge of matrix and linear algebra (e.g., 625.252 Linear Algebra and Its Applicationsor equivalent).