CS231n 2025 Lecture Notes
  • PDF
  1. 1  CS231n 2025 Lecture Notes
  • 1  CS231n 2025 Lecture Notes
  • Fundamentals
    • 2  Introduction
    • 3  Image Classification with Linear Classifiers
    • 4  Regularization and Optimization
    • 5  Neural Networks and Backpropagation
    • 6  Convolutional Networks
    • 7  CNN Architectures
    • 8  Recurrent Neural Networks
    • 9  Attention and Transformers
  • Vision Tasks
    • 10  Object Detection and Segmentation
    • 11  Video Understanding
  • Systems
    • 12  Large-Scale Distributed Training
    • 13  Self-Supervised Learning
  • Generative Models
    • 14  Generative Models I
    • 15  Generative Models II
  • Beyond 2D
    • 16  3D Vision
  • Multimodal
    • 17  Vision and Language
  • Embodied AI
    • 18  Robot Learning
  • Impact
    • 19  Human-Centered AI

CS231n 2025 Lecture Notes

Deep Learning for Computer Vision — Stanford University, Spring 2025

Modern, in-depth lecture notes for Stanford CS231n covering the 2025 curriculum: CNNs, Transformers, diffusion models, and vision-language models.
Author

Murat Raimbekov

CS231n lecture notes · Stanford · Spring 2025 · Unofficial

Eighteen lectures
of Stanford CS231n, written up.

Vision Transformers, contrastive pretraining, latent diffusion, segmentation foundation models, vision–language models — written from the 2025 lectures, with every result linked to the paper it came from.

Start with lecture 1 Read as PDF
conv 3×3 · stride 1 · activation map
TipHow to read these notes

Each lecture is a standalone page written to be read straight through rather than skimmed. Sections are numbered and individually linkable, so you can share a link to exactly the part you mean, and equations and figures are cross-referenced so a later lecture can point back at the thing it depends on.

Lectures

The course runs to 18 lectures, and all of them are written. The roadmap groups them by theme.

Lecture 1

Introduction

Why vision is the hard part of intelligence, how thirty years of geometry stalled on it, and what changed in 2012.

Complete

Lecture 2

Image Classification with Linear Classifiers

The classification setup, nearest neighbours, and why linear models are the right place to start.

Complete

Lecture 3

Regularization and Optimization

Why the data loss underdetermines a classifier, and how gradient descent and its variants find one anyway.

Complete

Lecture 4

Neural Networks and Backpropagation

What a hidden layer buys you, and how the chain rule on a graph gets the gradient of anything.

Complete

Lecture 5

Convolutional Networks

Building locality and translation into the layer itself.

Complete

Lecture 6

CNN Architectures

VGG, ResNet, and the recipe that gets a deep network to train at all.

Complete

Lecture 7

Recurrent Neural Networks

A state carried across time, one set of weights reused at every step, and the gradient problem that reuse creates.

Complete

Lecture 8

Attention and Transformers

Removing a bottleneck from a translation model, and the general-purpose primitive that fell out of it.

Complete

Lecture 9

Object Detection and Segmentation

What changes when the answer is no longer a single label, and how to ask a trained network where it was looking.

Complete

Lecture 10

Video Understanding

What a fourth axis costs and what it buys, from clip training to 3D convolution and the methods that reach past a few seconds.

Complete

Lecture 11

Large-Scale Distributed Training

What a GPU cluster actually is, and the five ways of cutting a transformer apart so that all of it has useful work to do.

Complete

Lecture 12

Self-Supervised Learning

Inventing tasks whose answers the data already knows, and the contrastive objective that eventually replaced all of them.

Complete

Lecture 13

Generative Models I

Modelling the distribution over images rather than the label given one: the chain rule, and the bound that buys a latent space.

Complete

Lecture 14

Generative Models II

Adversarial training and diffusion: a learned loss, a regression on noise, and the pipeline that ended up using both.

Complete

Lecture 15

3D Vision

Geometry has no canonical grid, so every method starts by choosing one. The map of those choices, and the decade-long tour across it.

Complete

Lecture 16

Vision and Language

Text was the supervision signal vision had been missing. What that bought, what it quietly failed to learn, and the four ways of building on it.

Complete

Lecture 17

Robot Learning

A robot’s output changes its next input, which breaks the assumption every earlier chapter rests on. Four answers, and what each one costs.

Complete

Lecture 18

Human-Centered AI

What the field is for. Two claims the closing lecture states informally, made precise on the contingency table underneath both.

Complete

What these notes are

The official cs231n.github.io notes are excellent — and they stopped being updated in 2017. Everything that has since reshaped computer vision is missing from them.

These notes are written from the Spring 2025 lecture recordings and slides, not summarised from the 2017 notes. That means they follow what the lecturers actually emphasised in 2025, including the parts that changed.

Each page aims to be:

  • Self-contained — you should not need the video open alongside it.
  • Honest about depth — core ideas get full derivations; peripheral ones get an intuition and a link to the paper.
  • Linked to sources — every result points at the original paper, not at a secondary summary.

Roadmap

Lectures are published as they are written, in course order, following the 2025 syllabus.

  1. Fundamentals — introduction, image classification, optimisation, backpropagation
  2. Convolutional networks — CNNs, architectures from AlexNet to ConvNeXt
  3. Sequence models — RNNs, attention, Transformers, ViT
  4. Vision tasks — detection, segmentation, video, 3D
  5. Generative models — VAEs, GANs, diffusion
  6. Advanced topics — NeRF, vision-language models, robot learning, ethics

Contributing

Found an error? Corrections are genuinely welcome — there is an Edit this page link at the bottom of every lecture, which opens a pull request in your browser. For anything larger, open an issue.

Disclaimer

This is an unofficial resource, not affiliated with Stanford University. For official course materials see cs231n.stanford.edu.

The notes are released under the MIT licence, which covers the writing and the diagrams made for this project. Figures reproduced from research papers and lecture slides remain the property of their original authors and are credited in their captions — see NOTICE.

2  Introduction
  • Edit this page
  • Report an issue