Stanford University · Course
Deep Generative Models (XCS236)
Deep Generative Models (XCS236) is a Stanford Online professional course, the professional version of CS236, on the probabilistic foundations and learning algorithms of deep generative models. It is taken online with live elements and leads to a Certificate of Achievement.
Who it suits
- Working engineers who want a Stanford course without applying to a graduate programme.
- Learners building toward the Artificial Intelligence Professional Program.
What it covers
- Autoregressive models and variational autoencoders.
- Normalizing flow models, generative adversarial networks and energy-based models.
- Applications of deep generative models in vision, speech and language.
Common questions about Deep Generative Models (XCS236)
- How much time does it take?
- Stanford lists 10 to 15 hours a week, with course materials available for 90 days after the course ends.
- What do I get at the end?
- A Certificate of Achievement; Stanford says you need to complete the required assignments and score 70% or higher.
- Can I enrol any time?
- Enrolment is only open during set periods, so check the page for the current dates and whether the course is open.
More like this
Keep learning on Infrato
- Path: AI for software developers
- More from Stanford University: all Stanford University listings in the directory
- Explore all AI courses
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.