Self-Driving Car Engineer Nanodegree vs Stanford CS229 Machine Learning

Reviewers praise the breadth — CV, sensor fusion, localisation, planning, control, ROS on Carla. The caveat is the curriculum is deep-learning-heavy and some flag this as the wrong architectural bet for real autonomous vehicles.

Sebastian Thrun, David Silver and the rotating industry instructors (Mercedes, BMW, NVIDIA, Uber ATG, Waymo alumni) get steady positive mentions. Reviewers who took the free CS373 first describe the nanodegree as a paid extension.

The biggest drag on the score. Original 2016-2017 price was ~$2,400; current pricing sits around $249-399/month, total ~$1,000-1,500. Flagged against free MIT 6.S094, MIT 6.832 and Stanford CS221/CS231n alternatives.

Original cohorts received mentor-graded project reviews and praised them highly, but later reviewers — including one of the most-cited HN voices — report Udacity "got rid of this feature" for self-paced learners. Slack community partially compensates.

Projects are unusually applied — behavioural cloning, lane finding, sensor fusion, path planning, and a final integration on Udacity's real Carla vehicle via ROS. The gap is that industry has moved past the deep-learning-heavy approach taught.

Reviewers consistently praise the mathematical depth — full derivations of GLMs, SVMs, EM, factor analysis and learning theory. The honest caveat is that the curriculum predates the Transformer era and deep learning gets brief treatment.

Andrew Ng's blackboard teaching gets repeated praise — one HN reviewer specifically prefers it to the Coursera version because he uses the board. The lecture pacing is academic and unhurried, which some find rigorous and others find slow.

Completely free — full 2018 lecture series on YouTube, all lecture notes, problem sets and section materials at cs229.stanford.edu. No certificate, no grading, no paywall. Reviewers consistently call it the highest-value rigorous ML resource available.

Zero official support for the YouTube cohort — no forum, no grading, no TA office hours, no cs50.ai-style tutor. Self-learners rely on community GitHub repos for solutions. Honest weakness, not unique to CS229.

Theory transfers durably — gradient descent, GLMs, regularisation, EM and learning theory remain foundational. The honest gap is that CS229 was not designed as a practical-first course; deployment, modern frameworks and Transformers are out of scope.