Stanford University · on Stanford Online

CS231n: Deep Learning for Computer Vision

4.9(9,000) on Stanford Online·1.5M enrolled
Advanced 50 hours EnglishFREE
Our recommendation
The definitive university course on deep learning for computer vision, from Stanford. It builds convolutional networks and modern vision models from the ground up, with excellent notes and assignments that are free online. Demanding, and no certificate from the free materials.

Good for: Learners with machine-learning basics who want to go deep on computer vision.

Less suitable if: You are new to machine learning, or you want a quick, applied tutorial.

Skills you'll gain

Deep learningComputer visionConvolutional neural networksImage classificationPyTorchNeural network training

Is this course right for you?

A good fit if you…

You know Python and machine-learning basics
You want to understand vision models deeply
You can work through demanding assignments

Consider something else if you…

You are new to machine learning
You want a short, applied course
You need a certificate

Requirements: Python, calculus, linear algebra and machine-learning basics. Advanced.

Realistic time: About 50 hours of lectures, plus substantial assignments.

About this course

CS231n is one of the most influential academic courses ever taught in machine learning — the course where convolutional neural networks for image recognition became mainstream, first delivered by Fei-Fei Li and Andrej Karpathy at Stanford. It covers convolutional network architecture in depth, backpropagation, training techniques (batch normalization, dropout, learning rate scheduling), object detection frameworks (YOLO, Faster R-CNN), image segmentation, recurrent networks for sequence tasks, and generative models (GANs, VAEs).

What you'll learn

Implement convolutional neural networks from scratch and understand their mechanics
Apply training techniques: batch normalization, dropout, and learning rate scheduling
Build and use object detection frameworks including YOLO and Faster R-CNN
Implement image segmentation models
Understand and implement generative models (GANs and VAEs)

This course includes

50h
On-demand video
Yes
Mobile access
English
Language

What it costs

The lecture notes and assignments are free and public on the course website. There is no certificate from the free materials.

Comparison · LBS

Compare alternatives for CS231n: Deep Learning for Computer Vision

Same topic, different options. We surface the trade-offs others hide so you can pick the course that actually fits your time, budget, and goals.
Stanford Online4.9(9,000)
CS231n: Deep Learning for Computer Vision
Price
Free
Free lecture materials; some versions paid
Duration
50 hrs
Level
Advanced
Certificate
Coursera
Introduction to TensorFlow for AI, ML and Deep Learning
Price
Free
Audit free · Certificate available
Duration
Level
Intermediate
Certificate
Professional Certificate
Udemy4.7(6,000)
Computer Vision with PyTorch: Deep Learning for Images
Price
Paid
One-time purchase, sales ~$15
Duration
20 hrs
Level
Intermediate
Certificate
Course Certificate
Coursera4.7(28,000)
TensorFlow Developer Professional Certificate
Price
Paid
Subscription-based, free to audit
Duration
160 hrs
Level
Intermediate
Certificate
Professional Certificate
Prices & availability can change — confirm on the provider's site. We're not affiliated with any single provider.

Instructor

FL
Fei-Fei Li / Andrej Karpathy
Stanford Online instructor
1.5M+ learners5 courses4.9 instructor rating

Originally taught by Fei-Fei Li (Stanford CS Professor, former Google Cloud AI Chief Scientist) and Andrej Karpathy (former Tesla AI Director, OpenAI founding member, now independent).

About this provider

SO
Stanford Online
Stanford University's online learning platform offering free and paid courses from Stanford faculty across AI, ML, medicine, and computer science.
Visit Stanford Online

Frequently asked questions

Yes. The lecture notes and assignments are public on the course website, free to use.
Python, some calculus and linear algebra, and machine-learning basics. It is an advanced course.
No. The materials are open, but there is no certificate.
The fundamentals it teaches — how vision networks are built and trained — remain the foundation, even as architectures evolve.
Yes. The assignments are demanding, which is also why it teaches so well.
For a deep understanding of computer vision, it is one of the best resources available.
Free
to audit
Enroll now