# Stanford University CS236: Deep Generative Models

https://deepgenerativemodels.github.io/syllabus.html

[ ![](https://deepgenerativemodels.github.io/img/stanfordlogo.jpg) ](http://stanford.edu/)
# [Deep Generative Models](https://deepgenerativemodels.github.io/)
#### CS236 - Fall 2023
* * *
## Detailed Syllabus
  

Current quarter's videos are available through [Panopto](https://stanford-pilot.hosted.panopto.com/Panopto/Pages/Sessions/List.aspx?folderID=e3a9ef4c-4783-498f-b0ec-b0750189ab83).  
Course notes are published [here](https://deepgenerativemodels.github.io/notes/index.html).   
| Week  | Date  | Lecture Topics  | Coursework  | Sections  |  
| --- | --- | --- | --- | --- |  
| 1  | Sep 27  |  Introduction ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture1_2023.pptx))   |   |  [Probability](https://cs229.stanford.edu/section/cs229-prob.pdf) and [Linear Algebra](https://cs229.stanford.edu/section/cs229-linalg.pdf)  |  
| 2  |  Oct 02 & Oct 04   |  Background ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture2.pdf)) + Autoregressive Models ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture3.pdf))   |  HW 1 Released (Oct 02)   | [PyTorch](https://docs.google.com/presentation/d/1fyPRy-tFxdvswz2p4HyH6TGkOQCVXAPS8gxzaTJH55s/edit#slide=id.p)  |  
| 3  |  Oct 09 & Oct 11  |  Maximum Likelihood Learning ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture4.pdf)) + VAEs ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture5.pdf))   |   | [CNNs, RNNs, Transformers](https://docs.google.com/presentation/d/1Z6jq9WNCBFy9cqhkWtNbQ-WhcYU_9g5s4-4qMKsoDNY/edit?usp=sharing)  |  
| 4  |  Oct 16 & Oct 18   |  VAEs ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture6.pdf)) + Normalizing Flows ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture7.pdf))   |  HW 1 due, HW 2 released (Oct 16)   |   |  
| 5  |  Oct 23 & Oct 25   |  Normalizing Flows ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture8.pdf)) + GANs ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture9.pdf))   |   |   |  
|   |   |  Project Proposal: Due Wednesday, October 25, 2023   |  
| 6  |  Oct 30 & Nov 01  |  GANs ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture10.pdf)) + Energy Based Models ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture11.pdf))   |  HW 2 due (Oct 30)   |   |  
| 7  |  Nov 06 & Nov 08  |  Energy Based Models ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture12.pdf)) + Score Based Models ([Slides](https://deepgenerativemodels.github.io/assets/slides/lecture%2013.pptx))   |  HW 3 released (Nov 06)   |   |  
|   |   |  Midterm: **Day** : Nov 10 - **Time** : 6-9pm - **Location** : CEMEX (Last names A-L), HEWLETT200 (Last names M-Z)   |  
| 8  |  Nov 13 & Nov 15   |  Energy Based Models ([Slides](https://deepgenerativemodels.github.io/assets/slides/lecture_14_comp.pptx)) + Evaluation of Generative Models ([Slides](https://deepgenerativemodels.github.io/assets/slides/lecture15.pdf))   |   |   |  
|   |   |  Project Progress Report: Due Wednesday, November 15, 2023   |  
| 9  |  Nov 20 & Nov 22   |  Thanksgiving Break   |  
| 10  |  Nov 27 & Nov 29  |  Score Based Diffusion Models ([Slides](https://deepgenerativemodels.github.io/assets/slides/lecture16-2023-comp.pptx)) + Discrete Latent Variable Models ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture17.pdf))   |  HW 3 due (Nov 27)   |   |  
| 11  |  Dec 04 & Dec 06   |  Diffusion Models for Discrete Data ([Slides](https://deepgenerativemodels.github.io/assets/slides/cs236_lecture18.pdf))   |   |   |  
|   |   |  Poster Presentation: Wednesday, December 6, 2023 from 3:00 pm - 6:00 pm   |  
| 12  |  Dec 11 & Dec 13   |  Finals Week   |  
|   |   |  Final Project Report: Due Monday, December 11, 2023   |  
* * *
## Additional Reading: Surveys and Tutorials
  

  1. [Generative Modeling by Estimating Gradients of the Data Distribution](http://yang-song.github.io/blog/2021/score/) Yang Song. Blog post on score-based generative models, May 2021.
  2. [How to Train Your Energy-Based Models.](https://arxiv.org/abs/2101.03288) Yang Song and Diederik P. Kingma. February 2021. 
  3. [Tutorial on Deep Generative Models.](https://ermongroup.github.io/generative-models/) Aditya Grover and Stefano Ermon. International Joint Conference on Artificial Intelligence, July 2018.
  4. [Tutorial on Generative Adversarial Networks.](https://sites.google.com/view/cvpr2018tutorialongans/) Computer Vision and Pattern Recognition, June 2018.
  5. [Tutorial on Deep Generative Models.](https://www.youtube.com/watch?v=JrO5fSskISY) Shakir Mohamed and Danilo Rezende. Uncertainty in Artificial Intelligence, July 2017.
  6. [Tutorial on Generative Adversarial Networks.](https://www.youtube.com/watch?v=AJVyzd0rqdc) Ian Goodfellow. Neural Information Processing Systems, December 2016.
  7. [Learning deep generative models.](https://www.cs.cmu.edu/~rsalakhu/papers/annrev.pdf) Ruslan Salakhutdinov. Annual Review of Statistics and Its Application, April 2015.