This class is an introduction to the practice of deep learning through the applied theme of building a self-driving car. It is open to beginners and is designed for those who are new to machine learning, but it can also benefit advanced researchers in the field looking for a practical overview of deep learning methods and their application.

Interested in the class? Here are some things you could do:

  1. Register an account on the site to stay up-to-date. The material for the course is free and open to the public.
  2. Follow the DeepTraffic and the DeepTesla tutorials, checkout the DeepTraffic leaderboard.
  3. Design and evaluate neural networks for the DeepTraffic Game and the DeepTesla Simulation in the browser.
  4. Watch the lectures and guest talks below.

*New* Interested in joining our team? Click to find out more.

Course Information:

  • Initial Offering: Winter 2017
  • Instructor: Lex Fridman
  • Contact: deepcars@mit.edu

Lecture Slides and Videos:

  • Lecture 1: Introduction to Deep Learning and Self-Driving Cars
    [ Slides ] - [ Lecture Video ]
  • Lecture 2: Deep Reinforcement Learning for Motion Planning
    [ Slides ] - [ Lecture Video ]
  • Lecture 3: Convolutional Neural Networks for End-to-End Learning of the Driving Task
    [ Slides ] - [ Lecture Video ]
  • Lecture 4: Recurrent Neural Networks for Steering through Time
    [ Slides ] - [ Lecture Video ]
  • Lecture 5: Deep Learning for Human-Centered Semi-Autonomous Vehicles
    [ Slides ] - [ Lecture Video ]

Guest Talks:

From Research to Reality: Testing Self-Driving Cars on Public Roads
CEO, nuTonomy and Research Scientist, MIT
Self-Driving Vehicles, SLAM, and Deep Learning
Professor, MIT
Technology, Policy and Vehicle Safety in the Age of AI
Professor, Stanford
Past, Present, and Future of Motion Planning in a Complex World
Professor, MIT
We Only Adopt What We Trust: Policy and the Business of Autonomy
White House Presidential Innovation Fellow, Office of Science and Technology Policy

Big Thanks

Support for this course was provided by the good folks at MIT-SUTD and the Toyota Class Action Settlement Safety Research and Education Program. The prizes for the competition were provided by our friends and fellow self-driving car engineers at Udacity. And none of it would be possible without the great community of bright young minds at MIT and beyond.