Stanford University · Course
CS231n: Deep Learning for Computer Vision
Stanford CS231n is a close study of deep learning architectures for computer vision, focused on end-to-end models for visual recognition tasks, particularly image classification. Students implement and train their own neural networks over ten weeks.
Who it suits
- Learners who want the details of how deep networks for images work, not just how to call a library.
- People comfortable with programming and the maths behind neural networks.
What it covers
- Visual recognition tasks such as image classification, localisation and detection.
- Deep learning architectures for vision, including convolutional networks.
- Implementing and training your own neural networks.
- A detailed understanding of current computer vision research.
Common questions about CS231n: Deep Learning for Computer Vision
- How long is the course?
- The course description says ten weeks.
- Which offering did we read?
- The Spring 2026 course site.
- Will I implement things myself?
- Yes. The description says students learn to implement and train their own neural networks.
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 2026-10-13. 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.