What’s New in Stanford’s CS231n 2025: Full Course Materials and Syllabus

Course Release

Stanford CS231n Spring 2025 (Computer Vision) course materials—including lecture videos, slides, and programming assignments—are now publicly available. The last public release of this course was in 2017.

Access Links

Video playlist: https://www.youtube.com/playlist?list=PLoROMvodv4rOmsNzYBMe0gJY2XS8AQg16

Course website: https://cs231n.stanford.edu/

Instructors

Fei‑Fei Li – Professor, Computer Science, Stanford University (lead of ImageNet)

Ehsan Adeli – Assistant Professor, Psychiatry & Behavioral Sciences & Computer Science, Stanford University

Justin Johnson – Assistant Professor, University of Michigan; former FAIR researcher

Zane Durante – PhD student, Stanford Computer Science

Course Focus

The course covers fundamentals and recent advances in deep learning for computer vision, emphasizing end‑to‑end models for image classification and related tasks such as object detection, segmentation, and video understanding.

Syllabus

Introduction to Deep Learning and Computer Vision

Image Classification and Linear Classifiers

Regularization and Optimization

Neural Networks and Backpropagation

Convolutional Neural Networks for Image Classification

Training and Architecture of CNNs

Recurrent Neural Networks (RNN)

Attention Mechanisms and Transformers

Object Detection and Image Segmentation

Video Understanding

Large‑Scale Distributed Training

Self‑Supervised Learning

Generative Models

3D Vision

Vision and Language

Robotics Learning

Human‑Centred AI

Review Sessions

Four dedicated review lectures are interleaved with the main material:

Python / NumPy

Backpropagation

PyTorch

RNN and Transformer

Prerequisites

Proficiency in Python, including NumPy (all assignments are in Python)

College‑level calculus and linear algebra (ability to compute derivatives, manipulate matrices and vectors)

Basic probability and statistics (e.g., Gaussian distribution, mean, standard deviation)

Code example

本文
约1000字
，建议阅读
5
分钟
李飞飞主讲的新版 CS231n（2025）课程及材料发布，含复习课与先修要求。