Skip to content
InfratoApp

Stanford University · Course

Deep Learning for Computer Vision (CS231N)

Deep Learning for Computer Vision (CS231N) on Stanford Online is a ten-week graduate course on neural-network methods for visual recognition. You implement, train and debug your own networks and study current computer vision research.

Open at Stanford University ↗Common questions

Who it suits

  • Programmers who want to understand how image classification, localisation and detection work, not only use a library.
  • People comfortable with Python and the maths of neural networks.

What it covers

  • End-to-end models for image classification, localisation and detection.
  • Learning algorithms such as backpropagation, and practical tricks for training and fine-tuning networks.
  • Recurrent networks and LSTMs, and supervised and unsupervised learning.
  • Implementing, training and debugging your own networks.

Before you start

  • Stanford lists a conferred bachelor’s degree with an undergraduate GPA of 3.0 or better.
  • Proficiency in Python, with assignments using NumPy.
  • College calculus and linear algebra, and basic probability and statistics.

Common questions about Deep Learning for Computer Vision (CS231N)

How long is it?
Stanford lists 10 weeks at 15 to 25 hours a week, and 4 academic units.
Do I need prior programming experience?
Stanford asks for proficiency in Python, and links a tutorial for those less familiar with it.
Can I enrol any time?
Enrolment is only open during set periods, and an application is needed for graduate courses, so check the page for the current dates.

More like this

Keep learning on Infrato

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.