Description: Lecture, four hours; discussion, two hours; outside study, six hours. Requisite: course M146. Fundamentals of variational autoencoders, generative adversarial networks, autoregressive models, normalizing flow models, energy-based models, diffusion models. Applications of generative models in reinforcement learning, scientific discovery, and societal challenges in high-stakes deployments. S/U or letter grading.

Units: 4.0