Skip to content
InfratoApp

Stanford University · Course

Deep Generative Models (CS236)

Deep Generative Models (CS236) on Stanford Online covers the probabilistic foundations and learning algorithms of deep generative models, such as autoregressive models, variational autoencoders and GANs. Stanford notes this listing is not currently offered and points to a professional version, XCS236.

Open at Stanford University ↗Common questions

Who it suits

  • Learners who already know machine learning and want the probabilistic foundations of generative models.
  • Readers deciding between this listing and the professional version of the course.

What it covers

  • Autoregressive models and variational autoencoders.
  • Normalizing flow models, generative adversarial networks and energy-based models.
  • Learning a data distribution, and applications in computer vision, speech and language processing.

Before you start

  • Stanford lists a conferred bachelor’s degree with an undergraduate GPA of 3.0 or better.
  • Basic machine learning from courses such as CS221, CS228, CS229 or CS230.
  • Proficiency in a programming language, preferably Python, and basic probability and calculus.

Common questions about Deep Generative Models (CS236)

Is it being offered?
Stanford’s page says CS236 has not been offered and points to a professional version, XCS236.
How long is it?
Stanford lists 10 weeks at 10 to 20 hours a week, for 3 academic units.
Where is the current version?
Look at the XCS236 listing on Stanford Online, and check the page for enrolment dates.

More like this

Keep learning on Infrato

Where this comes from

Written from Stanford University’s own pages, read on 2026-10-14. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with Stanford University and this is not an endorsement.