Stanford CS229 Machine Learning vs CS50's Introduction to Artificial Intelligence with Python

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.

Reviewers praise the breadth — search, knowledge, uncertainty, optimisation, learning, neural networks and language in seven weeks. The recurring caveat is that the curriculum is classical-AI heavy and the language week ends before Transformers.

Brian Yu is consistently described as clear, structured and good at categorising algorithms into themes. The frequent flag is that he is more measured than David Malan in CS50x — strong pedagogy, less of the live-lecture energy that made the original CS50 famous.

Completely free to audit, including all lectures, projects and the cs50.ai tutor "duck". Only the optional verified certificate via edX costs money (around $199). Reviewers consistently rank it among the highest-value free AI resources available.

The Ed Discussion forum is active and reviewers explicitly credit the cs50.ai tutor with helping them finish projects they would otherwise have abandoned. The honest catch is the multi-week wait for human grading reported by some learners.

Foundations transfer well — minimax, constraint satisfaction, Bayesian networks, basic neural networks — but reviewers note the course is a survey, not a path to production ML. You finish knowing what techniques exist, not how to ship a model on dirty data.