Class overview

Generative AI are unsupervised machine learning methods that can create a wide variety of data, such as images, videos, audio, text, and 3D models. Deep generative models are the fundamental tools behind generative AI. They combine the generality of probabilistic reasoning with the scalability of deep learning. This course will study the probabilistic foundations and learning algorithms in generative AI, including variational autoencoders, generative adversarial networks, autoregressive models, normalizing flow, and diffusion models. This is a graduate-level course with an emphasis on mathematical principles as well as practical know-how. The course will be a combination of lectures, student presentations, and team projects.

 Lecturer: Qi (Rose) Yu  (


Week 1 (Sep 25)                                        Introduction and deep learning recap                     

Week 2 (Oct 2)                                           Generative AI background                                          HW 1 release

Week 3 (Oct 9)                                            Autogressive Models                                                 

Week 4 (Oct 16)                                          Variational Autoencoder                                           Project Proposal Due  

Week 5 (Oct 23)                                           Generative Adversarial networks                           HW 2 release

Week 6 (Oct 30)                                            Normalizing Flow                                                      

Week 7 (Nov 6)                                           Energy-Based Model                                              Project Milestone Due 

Week 8 (Nov 13)                                           Diffusion Models                                                      HW3 release

Week 9 (Nov 20)                                           Guest Lecture / Thanksgiving                                          

Week 10 (Nov 27)                                           Evaluation and Applications                                 

Week 11 (Dec 4)                                            Final project presentation                                  Project Final Report Due


 Class Assessment



Q: What are the pre-requisites?

Q: Can masters/undergraduates take this course?


About me

My Chinese name is Qi Yu. That is also the instructor name in the registrar's office.  I publish under the name Rose Yu. You can learn more about my research at my personal website.