Stanford CS231n Core Topics Overview | Generated by AI

Home 2025.12

Question: What is the course syllabus for Stanford CS231n by Andrej Karpathy?

Answer:

Stanford CS231n, titled “Convolutional Neural Networks for Visual Recognition” (now often called “Deep Learning for Computer Vision”), was originally designed and primarily taught by Andrej Karpathy during its early offerings (Winter 2015 and Winter 2016 quarters). He created the foundational lecture notes, assignments, and much of the course structure that is still widely used today.

The classic syllabus from the Andrej Karpathy era (Winter 2016) covers the following main topics across approximately 20 lectures:

The course includes hands-on assignments implementing these concepts (e.g., kNN, fully-connected nets, ConvNets in frameworks like PyTorch/TensorFlow, network visualization) and a final project.

Note that the current version of CS231n (e.g., Spring 2025) has evolved under instructors like Fei-Fei Li and others, incorporating newer topics such as generative models, transformers in vision (ViTs), and human-centered AI, while retaining the core structure from Karpathy’s original design.

The original lecture notes from the Karpathy era remain publicly available and are still the most referenced version of the course materials.

References:


Back

x-ai/grok-4.1-fast

Donate