6.S094: Deep Learning for Self-Driving Cars

Interested in the class? Do the following:

1. First, create an account on this site to get updates (including lecture videos)
2. Second, if you're an MIT student register for the class here. If you're not an MIT student and would still like to sit in on the class, then send me an email at deepcars@mit.edu. If you just want to follow along online, create an account on the site and that's it. The material for the course is free and open to the public.
3. Third, look at the list of various resources that may help you with the class.

Course Information:

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.

• Where: 54-100 (see MIT map)
• Days: 9 lectures, Jan 9-20 (see schedule below)
• Times: Starts at 3pm. Expected lecture duration is 1 hour. Max time frame is 3-5pm.
• Max class size: 300
• Prerequisities: Basic programming experience. Python preferred.
• Units: 3
• Instructor:Lex Fridman
• Contact: deepcars@mit.edu

Guest Speakers:

* Material marked in red indicates links that are not yet active but will soon be.

Course Topics:

* Material marked in red indicates links that are not yet active but will soon be.

• Introduction to Deep Learning for Intelligent Systems
  [ Slides ] - [ Lecture Video ]
• Learning to Move: Reinforcement Learning for Motion Planning
• Learning to Drive: Convolutional Neural Networks and End-to-End Learning of the Full Driving Task
• Learning to Share: Driver State Detection and Shared Autonomy
• Learning to Think: The Road Ahead for Human-Centered Artificial Intelligence

Schedule: