Deep learning for self-driving cars


Prerequisites: None. Designed to be accessible for beginners.

Load: 3 P.M. - 5 P.M. on Jan. 9 - 13, 17 - 20 (Daily 2-hour lectures over two weeks).

Time Outside Class: 3-5 hours total to complete coursework. 10-20 hours total if you aim to win one of the two competitions.


An introduction to the practice of deep learning through the applied theme of building a self-driving car with shared control between "human" and "machine". This course is centered around two projects where students develop deep learning models that compete against each other in an online driving environment. The course 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 the big picture progress of deep learning as applied to the problem of autonomous driving.

Competitions will include:

#1 Autonomous Rat Race

#2 Massively Parallel Autonomous Road Trip Across America