Frequently Asked Questions

What’s up with lectures?

Lectures are Tuesdays & Thursdays 2:30-3:50PM PST over Zoom. Tuesdays will cover general material, and Thursdays will delve a bit deeper. Feel free to skip and post on Piazza if that’s more your jam.

What are some ways I can do lecture, if I like learning that way?

You can watch the lectures live by going to Canvas, and going to the Zoom tab. Recordings will also be posted after lecture onto Canvas.

What is the grading breakdown for this course?

  • 50%: Class project - creativity and equal participation within a group will be rewarded
  • 25%: Midterm
  • 25%: Programming assignments & quizzes
  • 0%: Attendance
  • Extra credit: Your (or your GAN-generated) Memes. Requirements: Relevant and Appropriate with capital R and A there.

What does each Coursera Module Contain?

One module of the GANs Specialization on Coursera includes:

  • Videos. These are organized in “weeks”. You will have to watch ≈10 videos (approx 10min each) every week.
  • In-video quizzes. These are sprinkled in every video for you to assess your understanding of the material.
  • Programming assignments (≈2h per week to complete). The programming assignments will usually lead you to build concrete algorithms, you will get to see your own result after you’ve completed all the code. It’s gonna be fun! For both assignment and quizzes, follow the deadlines on the Syllabus page, not on Coursera.

How do I submit assignments?

From the Coursera sessions (accessible from the invite you receive by email), you will be able to watch videos, solve quizzes and complete programming assignments. Each quiz and programming assignment can be submitted directly from the session and will be graded by our autograders.

You will submit your project deliverables on Gradescope. You should be added to Gradescope automatically by the end of the first week. If not you can join with course code TBD.

What is the late day policy?

No late days. We won’t grade them. You’ll probably still do fine in the class.

Is it okay to use a dataset that is not public?

Yes, but it’s not encourage. You will have to be able to describe it, and show generated data.

Can I share the CS236G project with another class’s project?

Yes, we’re OK with it – as long as your other class is OK with it. Just make sure to specify that you are doing that, and we ask that you have the same student partners there and here.

How many people can be on a team?

Max 2 people per team – or feel free to do the project alone. A larger team size will be taken under consideration when evaluating the scope of the project in breadth and depth, meaning that a 2-person team is expected to accomplish more than a 1-person team would.

Where can I find some project inspiration?

Awesome GAN

Is there a textbook or other resource I could use to supplement my learning?

Not officially, but great resources are Deep Generative Models (Ch. 20) in The Deep Learning book and Deep Learning (Ch. 21) in AI: A Modern Approach.

What if I need academic accommodations?

Students who may need an academic accommodation based on the impact of a disability must initiate the request with the Office of Accessible Education (OAE). Professional staff will evaluate the request with required documentation, recommend reasonable accommodations, and prepare an Accommodation Letter for faculty. Unless the student has a temporary disability, Accommodation letters are issued for the entire academic year. Students should contact the OAE as soon as possible since timely notice is needed to coordinate accommodations. The OAE is located at 563 Salvatierra Walk (phone: 723-1066).

What is the honor code policy like?

We strongly encourage students to form study groups. Students may discuss and work on programming assignments and quizzes in groups. However, each student must write down the solutions independently, and without referring to written notes from the joint session. In other words, each student must understand the solution well enough in order to reconstruct it by him/herself. In addition, each student should submit his/her own code and mention anyone he/she collaborated with. It is also an honor code violation to copy, refer to, or look at written or code solutions from a previous year, including but not limited to: official solutions from a previous year, solutions posted online, and solutions you or someone else may have written up in a previous year. Furthermore, it is an honor code violation to post your assignment solutions online, such as on a public git repo.

The Stanford Honor Code

The Stanford Honor Code as it pertains to CS courses

Can I audit CS236G?

Yes! If you have a Stanford ID. You’ll get access to some materials (but likely not all).