# lexfridman/mit-deep-learning

Tutorials, assignments, and competitions for MIT Deep Learning related courses.

Repository: https://github.com/lexfridman/mit-deep-learning
Canonical: https://ross.abutalabs.com/products/mit-deep-learning
Homepage: https://deeplearning.mit.edu
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: deep-learning, mit, self-driving-cars, deep-reinforcement-learning, deep-rl, artificial-intelligence, neural-networks, segmentation, machine-learning, data-science, deeplearning, tensorflow, tensorflow-tutorials, jupyter-notebooks
Last push: 2024-01-03T13:54:05+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3525, "days_push": 973, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10453, forks 2200 (observed 2026-08-28T04:10:42.029102+00:00)

## What it is
A collection of Jupyter notebook tutorials, assignments, and competition materials for MIT Deep Learning courses taught by Lex Fridman. It covers deep learning basics, semantic segmentation, GANs, and deep reinforcement learning with TensorFlow.

## Use cases
- learn deep learning fundamentals with hands-on notebooks
- practice semantic segmentation on driving scene video
- get started with GANs like BigGAN in TensorFlow
- train a neural network for the DeepTraffic reinforcement learning competition
- find course materials and lecture videos for MIT deep learning classes
- run tutorials in Google Colab without local setup

## When to choose
- you want structured, lecture-backed tutorials for learning deep learning
- you prefer runnable Jupyter/Colab notebooks over dry documentation
- you're interested in self-driving car applications of deep learning
- you want an introduction to deep reinforcement learning with a competition

## When to avoid
- you need production-ready deep learning code or libraries
- you want up-to-date coverage of the latest models and frameworks
- you need a comprehensive curriculum rather than selected course topics
- you prefer PyTorch over TensorFlow

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, machine-learning, computer-vision, reinforcement-learning
- domain: deep-learning, machine-learning, computer-vision, autonomous-vehicles, education, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, tensorflow, tutorials, self-driving-cars, gans, semantic-segmentation, deep-rl, mit-courses, colab

## Member repositories
- lexfridman/mit-deep-learning (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:42.029102+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:19:01.148637+00:00, confidence not recorded.
  - readme: https://github.com/lexfridman/mit-deep-learning (fetched 2026-08-28T04:10:42.029102+00:00, sha cf49020ad297)
  - homepage: https://deeplearning.mit.edu (fetched 2026-08-29T08:18:07.852842+00:00, sha 278745914341)
- Data as of 2026-08-30T08:39:29.467469+00:00.