lexfridman/mit-deep-learning

★ 10,440Jupyter NotebookAudience · generalComplexity · 1/5Setup · easy

Mindmap

mindmap
  root((repo))
    What it does
      Deep learning tutorials
      MIT course companion
      Browser-based notebooks
    Topics
      Neural network basics
      Image segmentation
      Generative AI
      DeepTraffic sim
    Format
      Jupyter notebooks
      Google Colab
      Video lectures
    Audience
      Students
      Beginners
      ML learners

mindmap root((repo)) What it does Deep learning tutorials MIT course companion Browser-based notebooks Topics Neural network basics Image segmentation Generative AI DeepTraffic sim Format Jupyter notebooks Google Colab Video lectures Audience Students Beginners ML learners

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Run interactive deep learning exercises in your browser without installing any software, using Google Colab.

USE CASE 2

Learn how neural networks make predictions by working through the step-by-step notebook on deep learning basics.

USE CASE 3

Train a model to label every pixel in a driving scene as road, car, or pedestrian using the image segmentation tutorial.

USE CASE 4

Experiment with generative adversarial networks to produce realistic images using the GAN tutorial notebook.

Tech stack

PythonJupyter NotebookGoogle Colab

Getting it running

Difficulty · easy Time to first run · 5min

In plain English

This repository is a collection of hands-on tutorials created to accompany MIT's deep learning courses, led by Lex Fridman and a small team at MIT. The tutorials are written as interactive notebooks, which means you can open them in your browser and run the code step by step without installing anything on your computer, thanks to Google Colab support. The tutorials cover several topics in machine learning. One introduces the basic building blocks of deep learning, including how neural networks take in data and make predictions. Another shows how an AI model can look at a video of driving and label every pixel as road, car, pedestrian, or another category. A third explores a type of AI called generative adversarial networks, where two models are trained against each other to produce realistic images. There is also a competition called DeepTraffic, where participants train a simulated car to drive as fast as possible through highway traffic. That component links out to its own repository and website. All the tutorials are paired with recorded lecture videos, written blog posts, and links to the underlying papers where relevant. The README itself is fairly short and the repository functions mainly as a companion to the MIT course materials rather than a standalone textbook.

Copy-paste prompts

Prompt 1

I just completed the deep learning basics notebook from lexfridman/mit-deep-learning. Help me modify the neural network to add an extra hidden layer and see how it changes accuracy.

Prompt 2

Using the image segmentation concepts from the MIT deep learning tutorials, help me write a Python script to segment a custom set of images using a pre-trained model.

Prompt 3

Explain how the GAN training loop works from the lexfridman/mit-deep-learning GAN notebook, what is the generator doing versus the discriminator and why do they compete?

Open on GitHub → Explain another repo

← lexfridman on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.