CS231n - Deep Learning for Computer Vision

---

Introduction

Back in 2023, CS231n helped me level up my deep learning fundamentals in a massive way. Even though it says “Computer Vision” in its name, it teaches far more than that 😍.

This was thanks to the legendary Winter 2016 YouTube offering, taught by Andrej Karpathy, Fei-Fei Li, and Justin Johnson.

Why does this page exist?

This website hosts all the notes I took while going through CS231n, especially the 2016 lectures.

My recommendation is to start with the 2016 version to build the fundamentals with minimum friction. You’ll enjoy the teaching style, and everything becomes easier when the basics click 🥰

Content

Slides from 2016 are available here.

Here’s the famous “Past to Present” map by Justin Johnson:

Lectures 🌠

Here are my notes for each lecture:

• 1. Intro to Computer Vision
• 2. Image Classification and Data-driven Approach
• 3. Linear Classification, Optimization, SGD
• 4. Backpropagation & Intro to Neural Networks
• 5. Training Neural Networks, Part 1
• 6. Training Neural Networks, Part 2
• 7. Convolutional Neural Networks
• 8. ConvNets for Spatial Localization & Object Detection
• 9. Understanding and Visualizing ConvNets
• 10. RNNs & LSTMs
• 11. Training ConvNets in Practice, Distributed Training
• 12. Overview of Caffe / Torch / Theano / TensorFlow
• 13. Segmentation
• 14. ConvNets for Videos
• 15. Closing and Guest Lecture

Looking for assignment notes? You’ll find them under Assignments.

For more projects and resources, see here.